Voice is quickly becoming the primary interface for consumer and enterprise devices, driven by improved speech models, small language models and the push for on-device processing to reduce latency and protect privacy. Delivering this experience requires always-on voice and audio pipelines—with features like keyword spotting, beamforming, ASR, noise reduction and immersive playback—under tight power budgets. This talk connects those requirements to silicon and software choices and introduces the sixth-generation Cadence Tensilica HiFi iQ DSP IP, designed for next-generation voice AI and immersive audio formats in markets such as smart home, mobile and automotive. We’ll explore architectural choices that enable higher efficiency and programmability—2x compute, 8x AI performance, and >25% energy savings versus HiFi 5s, expanded FP8/BF16 support and enhanced auto-vectorization—plus the developer ecosystem (NeuroWeave SDK, TensorFlow Lite Micro/LiteRT and ExecuTorch) that accelerates deployment.
HiFi iQ: Enabling Voice AI and Immersive Audio for Smart Home, Mobile and Automotive
Session Speakers
-
Amol Borkar
Group Director of Product Management and Marketing—Tensilica DSPs, Silicon Solutions Group (SSG), Cadence
Amol Borkar is the Group Director of Product Management and Marketing for Tensilica DSPs at Cadence. Since joining the company in 2018 as a Senior Product Manager, he has led the creation and launch of numerous successful hardware and software products across the Tensilica DSP portfolio. Amol’s leadership spans product management, product marketing, outbound strategy, partnerships and ecosystem development for the Vision, ConnX and MathX DSP families. Most recently, he expanded his responsibilities to also include Tensilica’s industry‑leading HiFi DSP product line. Before Cadence, Amol held a variety of engineering, product management and marketing roles within Intel’s RealSense Group, where he played a key role in driving the success of several flagship 3D camera products. Earlier in his career, as part of his PhD research, Amol developed computer vision‑based advanced driver‑assistance algorithms for autonomous vehicles—work that led to multiple journal and conference publications and earned him the 2011 Outstanding Researcher Award from Georgia Tech’s Center for Signal and Image Processing.
