HiFi Audio, Voice, and Speech
Put the WOW in Your Audio, Voice, and Speech Processing with HiFi DSPs
Looking for the best quality audio, voice, and/or speech processing core for your next design? With all the software already ported for immediate deployment?
Put the WOW in your SoC design with Cadence® Tensilica® HiFi Audio DSPs. More than 55 top-tier semiconductor companies and system OEMs have picked our HiFi Audio DSPs for their products, with good reason.
Expansive Range of Codecs
Cadence delivers the software support you need, with support for more than 125 audio, voice, speech recognition, and audio and voice enhancement software packages. No porting is required. You can also port your own proprietary software, porting completely in C while maintaining or surpassing the performance of assembly on other DSPs.
Your Choice of Four Cores
- The HiFi Mini Audio DSP—Our smallest, lowest power DSP core for always-listening voice trigger and voice recognition
- The HiFi 2 Audio DSP—This highly efficient DSP core provides the lowest power MP3 audio processing
- The HiFi EP Audio DSP—A superset of HiFi 2 with advanced optimizations for DTS Master Audio, improved voice pre- and post-processing, and improved cache memory subsystem
- The HiFi 3 Audio DSP—Full 32-bit processing makes this DSP super efficient for many of the audio enhancement algorithms, wideband voice codecs, and multi-channel audio
Features for a Wide Range of Audio, Voice, and Speech Processing
The Features You Need for Designs Ranging from Ultra-Low Power to High Performance
Audio DSP Plus Control
All Cadence Tensilica HiFi Audio DSPs are click-box additions to our customizable Xtensa® LX processor and include the base Xtensa instruction set. In other words, they are excellent targets for control applications as well as audio.
Customizable to Meet Your Requirements
Because our HiFi Audio DSPs use our Xtensa LX DPUs, you get all of the customization advantages that our DPUs are known for, along with incredible flexibility, including (but not limited to):
- Complete flexibility to add/configure caches and local memories
- Option to add direct RTL-like interfaces via Ports, Queues, and Lookup Interfaces
- Option to add custom instructions with full compiler support
See our Xtensa product section for more details.
MP3 playback requires just 5.7MHz when running at 128Kbps, 44.1KHz, and dissipates only 0.45mW in the TSMC® 65nm LP process (including memories) with our HiFi 2 Audio DSP. This assures you of more than 100 hours of battery life.
Optimized for Audio and Voice
Our HiFi Audio DSPs are optimized solutions for digital audio and voice. The performance levels of these DSPs approach those of fixed-gate implementations. They offer the flexibility, fast time-to-market, and lower risk of a processor-based solution, while simultaneously reducing silicon area and power consumption.
Our HiFi Audio DSPs utilize Xtensa LX processor technology with custom instructions (better code density, fewer cycles), flexible datapath widths (higher efficiency per cycles), multiple instructions per cycle (VLIW—higher efficiency per cycle), and simultaneous data operations (SIMD—parallelization). A comprehensive Eclipse-based software development environment is provided, with everything from a source code editor, debugger, and ISS to an optimized compiler for exceptional code density.
Optimized for Always-Listening Voice Trigger and Recognition
HiFi Mini is our smallest, lowest power DSP core supporting always-listening voice trigger and speech command modes. The HiFi Mini DSP IP core enables a hands-free experience. Cadence is working with Sensory and other software partners who provide innovative voice activation, speech command recognition, voice pre-processing and noise reduction products—all optimized on the HiFi Mini DSP.
We optimized the HiFi Mini DSP core to be as small and power-efficient as possible for voice trigger and voice recognition in two major ways. First, the core uses compact 40-bit encoding, which significantly improves code size. Second, we added efficient 16-bit instructions that are optimized for voice and audio codecs.
All the Digital Radio Codecs You Need
Our HiFi DSPs run all the decoders required around the world for digital audio, including:
- HD Radio™—From iBiquity™ Digital
- DAB—In the MP3 decoder
- DAB+—Certified by Dolby®
- DRM—Certified by Dolby
- XM-Satellite—From XM® Satellite
- T-DMB—In the BSAC decoder
- ISDB—In the AAC, HE-AAC decoders
Fully Programmable in C
All HiFi Audio DSPs are fully programmable in C, with no assembly required. So if you have proprietary algorithms to port for a HiFi DSP, it’s easy and quick.
Ready for Immediate Design-In
All HiFi DSPs are pre-packaged, ready to drop into DOC designs. They provide programmable support for over 90 audio, voice, and sound enhancement packages, which are pre-ported and ready to use, with no software porting required.
Capable of the Best Sound Enhancement Algorithms
Audio requirements for everything from smartphones to home stereo receivers are being driven by audio post-processing.
For voice, smartphone requirements are moving from narrowband to wideband codecs with improved noise suppression, noise dependent volume control, and other algorithms to improve sound quality in crowded environments.
For home and car audio, audio enhancement software is significantly enriching the user experience, creating important competitive advantages.
And gaming requirements in all environments are driving requirements for up to 32 streams for immersive play.
Efficient for Blu-ray Discs
Our HiFi Audio DSPs have been designed into Blu-ray Disc™, set-top box, and high-end home theater receiver SoCs.
Architectural enhancements to our HiFi EP significantly improves DTS Master Audio decoding and tolerance to high external memory latency. With HiFi EP, single-core Blu-ray Disc SoCs can easily be implemented in 65GP with additional MHz to spare for other audio functions.
The 32-bit architecture of our HiFi 3 DSPs significantly lowers the required MHz for complex audio enhancement algorithms, thus lowering the required power.
Performance to Spare
Because of the efficiency of Tensilica HiFi architectures, our HiFi Audio DSPs require only a fraction of the available MHz to perform audio decoding and encoding functions, leaving extra headroom for other control as well as media and signal-processing tasks.
HiFi Comparison Chart
What are the differences among the four Hifi Audio/Voice DSPs?
|HiFi Mini||HiFi 2||HiFi EP||HiFi 3|
|Slots for VLIW||2||2||2||3|
|MACs||24x24 32x16||24x24 32x16||24x24 32x16 32x24||4 MACs operating as: 4 24x24 or 4 32x16 or 2 32x32 or 2 32x24|
|DSP optimizations for voice pre- and post-processing||X||X|
|Predictive prefetch to improve performance of cache memory subsystem||X||X|
|DSP performance enhancements for FFT, FIR, and IIR||X|
|ITU support for voice codecs||X|
|Eclipse-based software development environment||X||X||X||X|
|Software Codec Library||X||X||X||X|
|DTS Master Audio|
Primary Audio: DTS Master Audio 24.5Mbps, 5.1 channels, 192kHz
Secondary Audio: DTS-LBR (DTS Express) 256Kbps, 48kHz Decoding
DTS Transcode, Upsample, Downsample, Mixing, Others
HiFi Audio Tunneling for Android Prolongs Battery Life
The Industry's Most Efficient, Lowest Power Way to Offload Audio/Voice in Your Android Device
The Cadence® Tensilica® HiFi Audio Tunneling (HAT) for Andoid solution allows OEMs to quickly take advantage of the new audio tunneling features contained in KitKat, the latest release of Android. Tremendous power savings are realized by completely offloading the audio decoding and post-processing functionality from the host CPU to the HiFI Audio DSP. Additionally, this audio tunneling solution allows the DSP to send the audio content directly out for retendering, eliminating the need to move uncompressed audio data back to the host. We estimate that this cuts audio power by up to 14X, thereby doubling phone mp3 playback.
The new Audio Tunneling feature in Android is the optimal audio offloading solution as it greatly reduces the amount of data passed back to the host from the DSP. See the chart below for an illustration of this reduced interprocessor communications.
NOTE: Above shows the amount of interprocessor data exchanged to decode 5 minutes of high quality MP3 (stereo, 256Kbps)
HAT Reference Design for Android
Cadence offers HAT, a solution which includes the HiFi Kernel drive and an audio framework. The HiFi Kernel driver loads the DSP firmware and manages interprocessor communications. The framework schedules the audio tasks and manages the audio processing components including codec and post-processing modules. This solution is available in source code format and can be easily adapted to a particular platform or SOC. Consulting services are available to port to a customer’s board.
Learn More - Watch our MWC Demo Video
Design Tools Speed Your Adoption and Integration Processes
The Industry's Most Powerful and Complete Design Environment
Port Software Quickly in C
A key advantage of the HiFi DSPs is that they use a simple programming model. Software developers can port audio, voice, and enhancement software codecs completely in C, while maintaining or surpassing the performance of assembly on other DSP and CPU architectures. This minimizes the time required to port and maintain special or proprietary audio software.
For Processor Designers
We deliver patented, proven tools that automate the process of generating your HiFi-based DPU along with matching software tools. These tools have been proven in hundreds of designs and the results are guaranteed correct by construction.
View the complete set of tools for processor designers.
For Software Developers
The Xtensa® Software Developer's Toolkit provides a comprehensive collection of code generation and analysis tools that speed the software development process. The Cadence Tensilica Eclipse-based Xtensa Xplorer Integrated Development Environment (IDE) serves as the cockpit for the entire development experience.
View the complete set of tools for software developers.
Audio, Voice, and Speech Software—Over 125 Codecs Available Now
Over 125 Software Packages Already Supported by HiFi
The following audio, voice, and audio and voice enhancement software packages are available for the HiFi DSPs. See the HiFi 2 & HiFi EP Audio/Voice DSP Product Brief for detailed information.
Audio & Voice Partners
HiFi Customers Are Designing Exciting Products
Used by the Best in the Industry
Cadence Tensilica HiFi Audio/Voice DSPs are at work in many popular products. See our Customer Profiles section to learn more.
Literature, Videos, and Other Resources—Learn More About HiFi Audio/Voice DSPs
Learn More About HiFi DSPs
|HiFi 2 & HiFi EP Audio/Voice DSP Product Brief|
|HiFi 3 High-Performance Audio/Voice DSP Product Brief|
|HiFi Mini Low-Power DSP Product Brief|
Hardware/Software Design Tools
|Xtensa Processor Developer's Toolkit Product Brief|
|Xtensa Software Developer's Toolkit Product Brief|
Watch Jason from RealTEK as he gives a hands-on demo of RealTEK's ALC5677 at the Consumer Electronics Show 2014 (CES2014). The ALC5677 is a HiFi audio CODEC integrated with Tensilica's HiFi EP DSP. The demo highlights voice trigger and voice command functionality and how this is an ideal audio solution for mobile devices.
Watch Jason from RealTEK as he gives a hands-on demo of RealTEK's ALC5677 at the Consumer Electronics Show 2014 (CES2014). The ALC5677 is a HiFi audio CODEC integrated with Tensilica's HiFi EP DSP. The demo highlights multi-microphone voice processing functionality and how this is an ideal audio solution for mobile devices.
Chris Rowen Discusses the Growing Demands of Audio Devices
Chris Rowen, Cadence Fellow, discusses the explosion of audio and the growing technical demands across a wide range of devices and applications at Globalpress 2012.