AIConfPaper
← Search

Alexander Gruenstein

8 accepted papers

2024

Improving Acoustic Echo Cancellation for Voice Assistants Using Neural Echo Suppression and Multi-Microphone Noise Reduction

Jens Heitkaemper, Arun Narayanan, Turaj Zakizadeh Shabestary, Sankaran Panchapagesan, James Walker, Bhalchandra Gajare +3
ICASSP 2024accepted

Keyword spotting (KS) and automatic speech recognition (ASR) on smart speakers in a home environment with interfering signals from loudspeakers are challenging tasks to this day, despite improvements in acoustic echo cancellation (AEC) systems. In this work we propose to combine a single microphone…

Cited by 0Source ↗Scholar ↗
2022

Improving The Latency And Quality Of Cascaded Encoders

Tara N. Sainath, Yanzhang He, Arun Narayanan, Rami Botros, Weiran Wang, David Qiu +19
ICASSP 2022accepted

In this paper, we explore reducing computational latency of the 2-pass cascaded encoder model [1]. Specifically, we experiment with reducing the size of the causal 1st-pass and adding capacity to the non-causal 2nd-pass, such that the overall latency can be reduced without loss of quality. In additi…

Cited by 0Source ↗Scholar ↗
2021

A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer and Large Scale Synthetic Data

Nathan Howard, Alex Park, Turaj Zakizadeh Shabestary, Alexander Gruenstein, Rohit Prabhavalkar
ICASSP 2021accepted

We consider the problem of recognizing speech utterances spoken to a device which is generating a known sound waveform; for example, recognizing queries issued to a digital assistant which is generating responses to previous user inputs. Previous work has proposed building acoustic echo cancellation…

Cited by 21Source ↗Scholar ↗
2021

Efficient Knowledge Distillation for RNN-Transducer Models

Sankaran Panchapagesan, Daniel S. Park, Chung-Cheng Chiu, Yuan Shangguan, Qiao Liang, Alexander Gruenstein
ICASSP 2021accepted

Knowledge Distillation is an effective method of transferring knowledge from a large model to a smaller model. Distillation can be viewed as a type of model compression, and has played an important role for on-device ASR applications. In this paper, we develop a distillation method for RNN-Transduce…

Cited by 0Source ↗Scholar ↗
2020

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Yanzhang He, Bo Li, Arun Narayanan, Ruoming Pang, Antoine Bruguier +22
ICASSP 2020accepted

Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art conventional models with respect to both quality, i.e., word error rate (WER), and latency, i.e., the time the hypothesis is finalized after the user stops speaking. In this paper, we develop a first-pass Recurrent…

Cited by 0Source ↗Scholar ↗
2019

Hotword Cleaner: Dual-microphone Adaptive Noise Cancellation with Deferred Filter Coefficients for Robust Keyword Spotting

Yiteng Arden Huang, Turaj Zakizadeh Shabestary, Alexander Gruenstein
ICASSP 2019accepted

This paper presents a novel dual-microphone speech enhancement algorithm to improve noise robustness of hotword (wake-word) detection as a special application of keyword spotting. It exploits two unique properties of hotwords: they are leading phrases of valid voice queries that we intend to respond…

Cited by 35Source ↗Scholar ↗
2019

Streaming End-to-end Speech Recognition for Mobile Devices

Yanzhang He, Tara N. Sainath, Rohit Prabhavalkar, Ian McGraw, Raziel Alvarez, Ding Zhao +14
ICASSP 2019accepted

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models must decode speech utterances in a streaming fashion, in rea…

Cited by 677Source ↗Scholar ↗
2016

Personalized speech recognition on mobile devices

Ian McGraw, Rohit Prabhavalkar, Raziel Alvarez, Montse Gonzalez Arenas, Kanishka Rao, David Rybach +5
ICASSP 2016accepted

We describe a large vocabulary speech recognition system that is accurate, has low latency, and yet has a small enough memory and computational footprint to run faster than real-time on a Nexus 5 Android smartphone. We employ a quantized Long Short-Term Memory (LSTM) acoustic model trained with conn…

Cited by 0Source ↗Scholar ↗