Portfolios - Page 3 of 7

Speex

Speex was developed as an open source standard in the year 2003. The codec operates on each 20 ms frame of 6-bit PCM speech signals sampled at 8 KHz, 16 KHz, or 32 KHz and generates a compressed bit-stream having bit-rates in the range of 2.15 kbps to 42.2 kbps respectively. Speex is based on Code Excited Linear Prediction (CELP) algorithm. The encoder provides an option of selecting the bit-rate using the quality index (varying from 0 – 10) and the degree of codebook search using the complexity index (varying from 0 – 10). The recommended complexity index is between 2 and 4. The decoder supports packet loss concealment and provides an option to generate either narrow band (8 KHz) or wide-band (16 KHz) speech output. Speex is designed for packet networks and voice over IP (VoIP) applications.

Based on Speex open-source standard version 1.2rc1.
Fixed-point ANSI C implementation.
Re-entrant implementation.
C-callable APIs.
Operates on 20ms frame size.
Operates on speech signals sampled at 16KHz or 8 KHz.
Supports bit-rates 2.15, 3.95, 5.95, 8, 11, 15, 18.2, and 24.6 kbps in narrow band (8 KHz) mode.
Supports bit-rates 3.95, 5.75, 7.75, 9.8, 12.8, 16.8, 20.6, 23.8, 27.8, 34.2, and 42.2 kbps in wide band. (16 KHz) mode.
Supports configuring the complexity level at init-time.
Supports configuring the quality or bit-rate at init-time.
Supports integrated Packet Loss Concealment (PLC) algorithm.
Optional support for xDM APIs for TI implementations.

Tested for bit-exactness with standard as well as a large database of non-standard test vectors.
Module is fully interruptible.
ARM implementation tested for any illegal memory access.
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation
Tested for 100% code coverage
Range validation for all the API parameters
Tested with scratch contamination at frame boundaries
Tested for packet loss conditions with 5% loss to 25% loss
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.
C55x implementation validated on C5510 and C5505 platforms.

ARM9E, ARM11, Cortex-A8, Cortex-A9, TI C64x+, TI C66x, and TI C55x.

SILK

SILK, super wide band speech coding standard, was developed by Skype in the year 2009. The codec operates on speech signals sampled from 8 48 KHz and generates compressed bit-streams with bit-rates ranging from 5 kbps to 40 kbps. Internally, the codec operates on four different audio bandwidths at sampling frequencies 8KHz, 12KHz, 16KHz or 24KHz. The bit-rate is adaptive and can be changed at 20 ms frame boundary; the internal frame size of SILK is 20 ms. The SILK encoder can be set to packetize maximum of five internal frames into a single frame output, allowing for 20, 40, 60, 80, or 100 ms frames of encoded speech. It also has an integrated voice activity detector, in-band forward error correction and packet loss concealment algorithm. The codec is highly scalable in terms of audio bandwidth, network bit rate, and complexity. It is the default codec for skype to skype VoIP calls.

Based on SILK SDK v1.0.7
Fixed point ANSI-C implementation
Re-entrant implementation
C-callable APIs
Operates on speech and mixed (speech and audio) signals sampled at 8 – 48 Khz
Support for bitrates ranging from 5kbps to 40kbps.
Support for all modes and ISF defined in the standard.
The bitrate can be configured at 20ms frame boundary.
Supports frame lengths of 20, 40, 60, 80, or 100 ms.
Support for SILK RTP payload and SILK storage bit-stream formats.
Supports integrated Packet Loss Concealment (PLC) algorithm.
Supports integrated Voice Activity Detection (VAD) algorithm.
Supports in-band forward error correction
Supports for complexity setting of encoder at init-time
Optional support for xDM APIs.
Option to specify the sampling frequency of the output PCM samples

Tested for bit-exactness with standard as well as a large database of non-standard test vectors
Module is fully interruptible.
Tested for any illegal memory access by the module
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation
Tested for 100% code coverage
Range validation for all the API parameters
Tested for Packet loss conditions with 5% loss to 25% loss
Tested with scratch contamination at frame boundaries
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.
C64x+ implementation validated on C6472EVM platform.
C66x implementation validated on C6678EVM platform.
AMD/Intel optimized implementation validated on Intel cores supporting SSE4 and above.

TI C66x, TI C64x+, ARM9E, ARM11, Cortex-A8, Cortex-A9, and AMD/Intel 64-bit cores supporting SSE4 and above

SBC

Sub-band Codec (SBC) was adopted as a mandatory codec by the Bluetooth Special Interest Group (SIG) in the year 2002. It operates on blocks of 4, 8, 12, or 16 16-bit PCM audio signals sampled at 16, 32, 44.1, or 48 KHz and generates a compressed bit-stream having bit-rates in the range of 56 512 kbps. The codec uses a cosine modulated filter bank for analysis and synthesis. The filter-bank can be configured for 4 or 8 bands. The sub-band signals are quantized using a dynamic bit-allocation scheme and block adaptive PCM quantization. The codec supports two bit allocation algorithms, loudness and SNR, and four channel modes: mono, stereo, joint stereo, and dual channel. The codec is primarily used in Bluetooth technology based short-range wireless applications.

Based on Bluetooth SIG A2DP Specification Revision V12
Optimized ASM/C implementation.
Re-entrant implementation
C-callable APIs
Generates 16-bit output audio signals sampled at 16, 32, 44.1, or 48 KHz.
Support for input block lengths of 4, 8, 12, or 16 samples.
Support for bit-rates ranging from 56 320 kbps for mono and 80 512 kbps for stereo.
Support for loudness and SNR bit allocation schemes.
Support for 4 or 8 sub-bands.
Support for mono, stereo, joint stereo, and dual channel modes.
Supports downmixing to mono output.
Supports Interleaved and de-interleaved output.
Supports Little-Endian implementation on ARM
Optional support for xDM API’s.

Tested for compliance using a large database of audio test vectors
Tested for loudness and SNR bit allocation schemes
Tested for 4 or 8 sub-band cases.
Tested for mono, stereo, joint-stereo, and dual channel test vectors.
Tested for graceful exit in case of bit-stream related errors or exception.
Tested for illegal memory access by the module on ARM platform.
Module is fully interruptible.
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation.
Tested with scratch contamination at frame boundaries
Tested for 100% code coverage
Range validation of all API parameters
ARM implementation is validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.

ARM9E, ARM11, Cortex-A8, and Cortex-A9

QCELP13k

QCELP13k is a variable rate speech codec standardized by TIA in 1997 and a revised description of this codec is given in TIA-733-A. QCELP13k operates on 14-bit speech signal sampled at 8 Khz and generates compressed bit-stream with four different rates namely full-rate (13.3kbps), half-rate (6.2kbps), quater-rate (2.7kbps) and eighth-rate (1kbps). It operates on frames of 20ms duration. Encoder selects appropriate rate depending on the speech activity: in full-rate mode 20ms frame encodes to 266 bits, in half-rate mode it encodes to 124 bits, in quarter-rate mode it encodes to 54 bits, and in eighth-rate mode it encodes to 20 bits. The speech coding algorithm is based on Code Excited Linear Prediction(CELP). QCELP13K is used in service option 17, a two-way voice communications between the base station and mobile station.

Based on TIA/EIA/IS-733 floating point specification.
Optimized C implementation (decoder).
Re-entrant implementation
C-callable APIs.
Support for 13.3 kbps, 6.2 kbps, 2.7kbps and 1 kbps bitrates.
Support for TTY/TDD signals as specified in the standard.
Supports integrated Packet Loss Concealment (PLC) algorithm.
Support for post-filter operation, configurable at frame boundary.
Supports decoding of QCP streams as per RFC3625.
Optional support for decoding of 3g2 streams.
Optional support for xDM APIs.
Support for Little Endian implementation on ARM.

Fixed-point implementation is tested objectively for PESQ, Log likelihood ratio, weighted spectral slope and segmental SNR.
Module is fully interruptible.
ARM implementation tested for any illegal memory access.
Tested for compliance with register preservation requirements.
Tested for Input buffer corruption.
Tested for I/O buffer alignment requirements.
Tested for multi-instance implementation.
Tested for 100% code coverage.
Tested with scratch contamination at frame boundary.
Range validation for all the API parameters.
Tested for packet loss conditions with 5% loss to 25% loss.
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.

ARM9E, ARM11, Cortex-A8, and Cortex-A9

MP3 Decoder

MPEG-1 Layer 3 or MP3 was standardized by ISO/IEC in 1993. The standard operates on 16/24-bit mono or 2-channel (stereo) audio signals sampled at 32khz, 44.1khz, or 48khz and generates compressed bit-streams having bit-rates ranging from 32 kbps to 320 kbps per channel. The MPEG-2 Layer 3, standardized in 1995, extended the algorithm to support lower sampling frequencies (16 khz, 22.05khz, 24 khz) and additional bit-rates ranging from 8 kbps to 160 kbps. MPEG-2.5 Layer 3 (an unofficial extension) further defines support for 8khz, 11.025khz, 12khz sampling frequencies. MPEG Audio standard also defines low complexity Layer 1 (MP1) and medium complexity Layer 2 (MP2) with bit-rates ranging from 32kbps to 448kbps and 8kbps to 384kbps respectively. Psychoacoustic model, Modified Discrete Cosine Transform (MDCT) and Huffman coding play a vital role in achieving high compression ratios. MP3 is the most popular audio codec used in the industry today and has been extensively deployed in portable media players, mobile phones, as well as network connected devices

Based on the ISO/IEC 11172-3, ISO/IEC 13818-3, and ISO/IEC 14496-3 standards
Optimized ASM/C implementation.
Re-entrant implementation
C-callable APIs
Supports decoding of MPEG-1, MPEG-2 and MPEG-2.5 streams.
Supports decoding of Layer 1, Layer 2 and Layer 3 streams.
Supports sampling frequencies 8, 11.025, 12, 16, 22.05, 24, 32, 44.1, and 48KHz respectively.
Supports for 16/24-bit PCM output.
Supports bit-rates ranging from 8kbps to 448kbps, depending on MPEG and layer versions.
Supports decoding of free-format bit-rate streams.
Support for mono and 2-channel stereo output.
Support for optional downmixing from stereo to mono.
Support for little-endian implementation on ARM9E.
Supports Interleaved and de-interleaved output.
Optional support for decoding of ID3v1 and ID3v2 tags.
Optional support for xDM APIs.

Implementation is tested for wide range of standard and non-standard test vectors.
Tested for various options such of MS/Intensity stereo, CBR/VBR, Long/Short blocks, CRC and bit-reservoir.
Tested for conformance as per the criteria specified in ISO/IEC 11172-4.
Tested for graceful exit in case of bit-stream related errors or exception.
Tested for illegal memory access by the module on ARM platform.
Module is fully interruptible.
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation.
Tested with scratch contamination at frame boundaries
Tested for 100% code coverage
Range validation of all API parameters
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.
Cortex-M4 implementation validated on the TI Tiva TM4C1294 EVM.

ARM9E, ARM11, Cortex-M4, Cortex-A8, and Cortex-A9

iLBC

Internet Low Bit Rate Codec (ILBC) was standardized by Global IP Sound (GIPS) in 2002. The codec operates on 20 or 30 ms, 16-bit PCM input speech signals sampled at 8 KHz, and generates a compressed bit-stream having a bit-rate of 15.2 or 13.3 kbps respectively. It uses a block independent linear prediction coding technique that prevents propagation of errors across frames. The codec has an inherent support for voice activity detection and packet loss concealment. The codec is royalty free and is used in voice over cable/IP, audio teleconferencing, streaming, archival, and messaging applications. It is one of the codecs supported by the Google WebRTC.

ARM implementation is based on floating-point ANSI-C specifications in RFC3951
C6x/AMD/Intel implementation is based on fixed-point reference c-code available as part of WebRTC project.
Optimized ASM/C fixed-point implementation
Re-entrant implementation
C-callable APIs
Operates on 16-bit PCM speech signals sampled at 8 KHz
Support for 15.2 and 13.3 kbps bit-rates
Support for RTP payload format as specified in RFC 3952.
Supports integrated Packet Loss Concealment (PLC) algorithm.
Support for bad frame indication at frame boundary.
Support for little-endian implementation (ARM)
Support for big- and little-endian implementation (TI C6x)
TI C66x/C64x+ implementation bit-compliant with Google WebRTC
Optional support for xDM APIs.
C6x implementation supports VAD/DTX/CNG, integrated from WebRTC project

ARM implementation tested objectively and via listening tests using a large database of speech test vectors
C6x implementated tested for bit-compliance with the fixed-point C reference available with WebRTC project
Module is fully interruptible
Tested for any illegal memory access by the module
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation
Tested for 100% code coverage
Range validation for all the API parameters
Tested with scratch contamination at frame boundaries
Tested for packet loss conditions with 5% loss to 25% loss
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.
C66x implementation validated on the C6678 EVM platform
C64x+ implementation validated on the C6472 EVM platform
C6x implementations are integrated with WebRTC application and validated for interoperability
AMD/Intel optimized implementation validated on Intel cores supporting SSE4 and above.

TI C64x+, TI C66x, ARM9E, ARM11, Cortex-A8, Cortex-A9, and AMD/Intel 64-bit cores supporting SSE4 and above.

H264 HP Decoder

H264 is a widely accepted video coding standard that was jointly developed by Video Coding Experts Group (VCEG) of the ITU-T and the Moving Picture Experts Group (MPEG) of ISO/IEC. It uses state-of-the-art coding tools and provides enhanced coding efficiency for a wide range of applications, including video telephony, video conferencing, TV, storage, streaming video and many others. H.264 standard defines several profiles and levels that specify restrictions on the bit stream and hence limits the capabilities needed to decode the bit streams. High profile improves objective compression quality (especially HD video) and also improves subjective compression capability with support for quantization weighting matrices with addition of lower computational complexity.

Based on the ISO/IEC 14496-10 standard
Optimized ASM/C implementation.
Re-entrant implementation
C-callable APIs
Up to level 5 features of high profile supported.
Progressive, interlaced, Picture Adaptive Frame Field (PicAFF), and Macro Block Adaptive Frame Field (MBAFF) type picture decoding supported.
Multiple slices and multiple reference frames supported.
CAVLC and CABAC decoding supported
All intra-prediction and inter-prediction modes supported.
Block sizes of 4×4 and 8×8 supported.
Supports scaling matrices.
Frame cropping supported.
Frame width of the range of 32 to 1920 pixels supported.
Byte-stream syntax for the input bit stream supported.
Parsing of Supplemental Enhancement Information (SEI) and Video Usability Information (VUI) supported
Long term reference frame and adaptive reference picture marking supported.
Gaps in the frame number supported.
Skipping of non reference pictures supported
Configurable delay for display of frames supported.
Separate quantization parameter for CB and CR chroma components supported.
Outputs are available in YUV 420 planar formats.
Compliant with xDM 1.0 IVIDDEC2 APIs.

Implementation is tested for all JVT test streams
Implementation is tested for wide range of non-standard test vectors for all levels
Tested with error streams. Corrupted streams includes NAL, slice, MB level data & header corruptions.
Tested with 3gpp error pattern corrupted streams.
Tested for resource usage (DMA channels, params etc)
Tested for illegal memory access by the module.
Module is fully interruptible.
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation.
Tested with scratch contamination at frame boundaries
Tested for 100% code coverage
Range validation of all API parameters
Validated on eInfochips C6472EVM.

TI C64x+ and TI C66x

H264 MP Decoder

H264 is a widely accepted video coding standard that was jointly developed by Video Coding Experts Group (VCEG) of the ITU-T and the Moving Picture Experts Group (MPEG) of ISO/IEC. It uses state-of-the-art coding tools and provides enhanced coding efficiency for a wide range of applications, including video telephony, video conferencing, TV, storage, streaming video and many others. H.264 standard defines several profiles and levels that specify restrictions on the bit stream and hence limits the capabilities needed to decode the bit streams. The main profile provides additional tools such as B-Slices for greater coding efficiency, weighted prediction for providing increased flexibility in creating motion-compensated prediction block and an alternative entropy coding method called CABAC (Context Adaptive Binary Arithmetic Coding). The potential applications of Main Profile include television broadcasting and storage.

Based on the ISO/IEC 14496-10 standard
Optimized ASM/C implementation.
Re-entrant implementation
C-callable APIs
Up to level 3 features of main profile supported.
Progressive, interlaced, Picture Adaptive Frame Field (PicAFF), and Macro Block Adaptive Frame Field (MBAFF) type picture decoding supported
Multiple slices and multiple reference frames supported.
CAVLC and CABAC decoding supported
All intra-prediction and inter-prediction modes supported.
Block sizes of 4×4 supported.
Frame cropping supported
Frame width of the range of 32 to 720 pixels supported.
Byte-stream syntax for the input bit stream supported.
Parsing of Supplemental Enhancement Information (SEI) and Video Usability Information (VUI) supported
Long term reference frame and adaptive reference picture marking supported.
Gaps in the frame number supported.
Skipping of non reference pictures supported
Configurable delay for display of frames supported.
Outputs are available in YUV 420 planar formats.
Optional support for xDM 1.0 IVIDEC2 APIs.

Implementation is tested for all JVT test streams
Implementation is tested for wide range of non-standard test vectors for all levels
Tested with error streams. Corrupted streams includes NAL, slice, MB level data & header corruptions.
Tested with 3gpp error pattern corrupted streams.
Tested for resource usage.(DMA channels, params etc)
Tested for illegal memory access by the module.
Module is fully interruptible.
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation.
Tested with scratch contamination at frame boundaries
Tested for 100% code coverage
Range validation of all API parameters.
Validated on eInfochips C6472 EVM.

TI C64x+ and TI C66x

GSM-HR

GSM Half Rate (GSM-HR) speech codec was developed in the 1990s and was adopted by the 3GPP for mobile telephony. The codec operates on each 20 ms frame of speech signals sampled at 8 KHz and generates compressed bit-streams with an average bit-rate of 5.6 kbps. The codec uses Vector Sum Excited Linear Prediction coder (VSELP) technique to compress speech. The codec provides voice activity detection (VAD) and comfort noise generation (CNG) algorithms and an inherent packet loss concealment (PLC) algorithm for handling frame erasures. The codec was primarily developed for mobile telephony over GSM networks.

Based on 3GPP specification.
Optimized C implementation.
Re-entrant implementation.
C-callable APIs.
Operates on speech signal sampled at 8 KHz.
Support for bit rate 5.6 kbps.
Supports integrated Packet Loss Concealment (PLC) algorithm.
The codec supports integrated Voice Activity Detection (VAD) algorithm configurable at init-time.
Optional support for xDM APIs.
The implementation supports both Little-Endian and Big-Endian versions.

Tested for bit exactness with the standard as well as large database of non-standard test vectors.
Module is fully interruptible. Maximum interrupt latency on C64x+ is 6000 cycles.
Tested for any illegal memory access by the module.
Tested for compliance with register preservation requirements.
Tested for Input buffer corruption.
Tested for I/O buffer alignment requirements.
Tested for multi-instance implementation.
Tested for 100% code coverage.
Range validation for all the API parameters.
Tested for Packet loss conditions with 5% loss to 25% loss.
TI C64x+ implementation validated on Spectrum Digital C6455 DSK.
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platform.
AMD/Intel optimized implementation validated on Intel cores supporting SSE4 and above.

ARM9E, ARM11, Cortex-A8, Cortex-A9, TI C64x+, TI C66x, and AMD/Intel 64-bit cores supporting SSE4 and above.

GSM-FR

GSM Full Rate (GSM-FR) speech codec was developed in early 1990s and was adopted by the 3GPP for mobile telephony. The codec operates on each 20 ms frame of speech signals sampled at 8 KHz and generates compressed bit-streams with an average bit-rate of 13 kbps. The codec uses Regular Pulse Excited Long Term Prediction Linear Predictive Coder (RPE-LTP) technique to compress speech. The codec provides voice activity detection (VAD) and comfort noise generation (CNG) algorithms and an inherent packet loss concealment (PLC) algorithm for handling frame erasures. The codec was primarily developed for mobile telephony over GSM networks

Based on 3GPP specification.
Optimized C implementation.
Re-entrant implementation.
C-callable APIs.
Operates on speech signal sampled at 8 KHz.
Support for bit rate 13 kbps.
Supports integrated Packet Loss Concealment (PLC) algorithm.
The codec supports integrated Voice Activity Detection (VAD) algorithm configurable at init-time.
Optional support for xDM APIs.
The implementation supports both Little-Endian and Big-Endian versions

Tested for bit exactness with the standard as well as large database of non-standard test vectors
Module is fully interruptible. Maximum interrupt latency on C64x+ is 6000 cycles.
Tested for any illegal memory access by the module
Tested for compliance with register preservation requirements
Tested for Input buffer corruption
Tested for I/O buffer alignment requirements
Tested for multi-instance implementation
Tested for 100% code coverage
Range validation for all the API parameters
Tested for Packet loss conditions with 5% loss to 25% loss
TI C64x+ implementation validated on Spectrum Digital C6455 DSK
ARM implementation validated on OMAP3530 (Cortex-A8) and DM6446/DM6467 (ARM926EJ-S) platforms.
AMD/Intel optimized implementation validated on Intel cores supporting SSE4 and above.

ARM9E, ARM11, Cortex-A8, Cortex-A9, TI C64x+, TI C66x, and AMD/Intel 64-bit cores supporting SSE4 and above.

SPEEX

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

SILK

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

SBC

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

QCELP-13K

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

MP3 DECODER

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

ILBC

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

H264 HP DECODER

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

H264 MP DECODER

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

GSM-HR

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details

GSM-FR

CODEC OVERVIEW

SALIENT FEATURES

TESTING FEATURES

AVAILABLE PLATFORM(S)

For datasheet with resource usage details