Search Results for author:
Found 7 papers, 3 papers with code
4-bit Conformer with Native Quantization Aware Training for Speech Recognition
Reducing the latency and model size has always been a significant research problem for live Automatic Speech Recognition (ASR) application scenarios.
A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization
We also show that learning a speaker-embedding space can scale further and reduce the amount of personalization training data required per speaker.
Real time spectrogram inversion on mobile phone
In this paper, we focus on methods for real time spectrogram inversion, where an algorithm receives a portion of the input signal (e. g., one frame) and processes it incrementally, i. e., operating in streaming mode.
Pareto-Optimal Quantized ResNet Is Mostly 4-bit
In this work, we use ResNet as a case study to systematically investigate the effects of quantization on inference compute cost-quality tradeoff curves.
Streaming keyword spotting on mobile devices
In this work we explore the latency and accuracy of keyword spotting (KWS) models in streaming and non-streaming modes on mobile phones.
Ranked #10 on
Keyword Spotting
on Google Speech Commands
Audio and Speech Processing Sound
Low-bit quantization and quantization-aware training for small-footprint keyword spotting
We investigate low-bit quantization to reduce computational cost of deep neural network (DNN) based keyword spotting (KWS).
THE EFFECTIVENESS OF A TWO-LAYER NEURAL NETWORK FOR RECOMMENDATIONS
We present a personalized recommender system using neural network for recommending products, such as eBooks, audio-books, Mobile Apps, Video and Music.
