46 citations · 82 across the 9 of their papers we have counts for
12 papers
Turn-taking and Backchannel Prediction with Acoustic and Large Language Model Fusion
Jinhan Wang, Long Chen, Aparna Khare +6
We propose an approach for continuous prediction of turn-taking and backchanneling locations in spoken dialogue by fusing a neural acoustic model with a large language model (LLM).…
Guided contrastive self-supervised pre-training for automatic speech recognition
Aparna Khare, Minhua Wu, Saurabhchand Bhati +2
Contrastive Predictive Coding (CPC) is a representation learning method that maximizes the mutual information between intermediate latent representations and the output of a given…
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
Gokce Keskin, Minhua Wu, Brian King +5
Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design de…
Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Swayambhu Nath Ray, Minhua Wu, Anirudh Raju +7
Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly…
Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition
Bhargav Pulugundla, Yang Gao, Brian King +5
Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this wo…
Wav2vec-C: A Self-supervised Model for Speech Representation Learning
Samik Sadhu, Di He, Che-Wei Huang +6
Wav2vec-C introduces a novel representation learning technique combining elements from wav2vec 2.0 and VQ-VAE. Our model learns to reproduce quantized representations from partiall…
Robust Multi-channel Speech Recognition using Frequency Aligned Network
Taejin Park, Kenichi Kumatani, Minhua Wu +1
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling…
Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning
Sanna Wager, Aparna Khare, Minhua Wu +2
In this work, we investigated the teacher-student training paradigm to train a fully learnable multi-channel acoustic model for far-field automatic speech recognition (ASR). Using…
Multi-channel Acoustic Modeling using Mixed Bitrate OPUS Compression
Aparna Khare, Shiva Sundaram, Minhua Wu
Recent literature has shown that a learned front end with multi-channel audio input can outperform traditional beam-forming algorithms for automatic speech recognition (ASR). In th…
Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition
Kenichi Kumatani, Minhua Wu, Shiva Sundaram +2
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrad…
Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition
Minhua Wu, Kenichi Kumatani, Shiva Sundaram +2
Conventional far-field automatic speech recognition (ASR) systems typically employ microphone array techniques for speech enhancement in order to improve robustness against noise o…
Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning
Ladislav Mošner, Minhua Wu, Anirudh Raju +5
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean an…