AIConfPaper
← Search

Turaj Zakizadeh Shabestary

4 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 ↗
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 ↗
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 ↗
2018

Supervised Noise Reduction for Multichannel Keyword Spotting

Yiteng Huang, Thad Hughes, Turaj Zakizadeh Shabestary, Taylor Applebaum
ICASSP 2018accepted

This paper presents a robust, small-footprint, far-field keyword spotting (KWS) algorithm, which was inspired by the human auditory system's ability to achieve the so-called cocktail party effect in adverse acoustic environments. It introduces the idea of combining microphone-array speech enhancemen…

Cited by 0Source ↗Scholar ↗