35 citations · 94 across the 19 of their papers we have counts for
24 papers
Two-pass Endpoint Detection for Speech Recognition
Anirudh Raju, Aparna Khare, Di He +9
Endpoint (EP) detection is a key component of far-field speech recognition systems that assist the user through voice commands. The endpoint detector has to trade-off between accur…
Cross-utterance ASR Rescoring with Graph-based Label Propagation
Srinath Tankasala, Long Chen, Andreas Stolcke +6
We propose a novel approach for ASR N-best hypothesis rescoring with graph-based label propagation by leveraging cross-utterance acoustic similarity. In contrast to conventional ne…
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Feng-Ju Chang, Anastasios Alexandridis, Rupak Vignesh Swaminathan +6
To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. T…
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…
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
Viet Anh Trinh, Pegah Ghahremani, Brian King +3
We present an approach to reduce the performance disparity between geographic regions without degrading performance on the overall user population for ASR. A popular approach is to…
VADOI:Voice-Activity-Detection Overlapping Inference For End-to-end Long-form Speech Recognition
Jinhan Wang, Xiaosu Tong, Jinxi Guo +2
While end-to-end models have shown great success on the Automatic Speech Recognition task, performance degrades severely when target sentences are long-form. The previous proposed…
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…
SynthASR: Unlocking Synthetic Data for Speech Recognition
Amin Fazel, Wei Yang, Yulan Liu +4
End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model require…
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…
REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling
Hu Hu, Xuesong Yang, Zeynab Raeesy +6
Accents mismatching is a critical problem for end-to-end ASR. This paper aims to address this problem by building an accent-robust RNN-T system with domain adversarial training (DA…
Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition
Jinxi Guo, Gautam Tiwari, Jasha Droppo +4
In this work, we propose a novel and efficient minimum word error rate (MWER) training method for RNN-Transducer (RNN-T). Unlike previous work on this topic, which performs on-the-…
Streaming ResLSTM with Causal Mean Aggregation for Device-Directed Utterance Detection
Xiaosu Tong, Che-Wei Huang, Sri Harish Mallidi +5
In this paper, we propose a streaming model to distinguish voice queries intended for a smart-home device from background speech. The proposed model consists of multiple CNN layers…
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Surabhi Punjabi, Harish Arsikere, Zeynab Raeesy +11
Multilingual ASR technology simplifies model training and deployment, but its accuracy is known to depend on the availability of language information at runtime. Since language ide…
Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition
Maarten Van Segbroeck, Harish Mallidih, Brian King +3
Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over…
Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
Chander Chandak, Zeynab Raeesy, Ariya Rastrow +5
This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for vo…
DiPCo -- Dinner Party Corpus
Maarten Van Segbroeck, Ahmed Zaid, Ksenia Kutsenko +7
We present a speech data corpus that simulates a "dinner party" scenario taking place in an everyday home environment. The corpus was created by recording multiple groups of four A…
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…
LSTM-based Whisper Detection
Zeynab Raeesy, Kellen Gillespie, Zhenpei Yang +6
This article presents a whisper speech detector in the far-field domain. The proposed system consists of a long-short term memory (LSTM) neural network trained on log-filterbank en…
Device-directed Utterance Detection
Sri Harish Mallidi, Roland Maas, Kyle Goehner +3
In this work, we propose a classifier for distinguishing device-directed queries from background speech in the context of interactions with voice assistants. Applications include r…
Estimating parameters of nonlinear systems using the elitist particle filter based on evolutionary strategies
Christian Huemmer, Christian Hofmann, Roland Maas +1
In this article, we present the elitist particle filter based on evolutionary strategies (EPFES) as an efficient approach for nonlinear system identification. The EPFES is derived…
The NLMS algorithm with time-variant optimum stepsize derived from a Bayesian network perspective
Christian Huemmer, Roland Maas, Walter Kellermann
In this article, we derive a new stepsize adaptation for the normalized least mean square algorithm (NLMS) by describing the task of linear acoustic echo cancellation from a Bayesi…
Spatial Diffuseness Features for DNN-Based Speech Recognition in Noisy and Reverberant Environments
Andreas Schwarz, Christian Huemmer, Roland Maas +1
We propose a spatial diffuseness feature for deep neural network (DNN)-based automatic speech recognition to improve recognition accuracy in reverberant and noisy environments. The…
A Bayesian Network View on Acoustic Model-Based Techniques for Robust Speech Recognition
Roland Maas, Christian Huemmer, Armin Sehr +1
This article provides a unifying Bayesian network view on various approaches for acoustic model adaptation, missing feature, and uncertainty decoding that are well-known in the lit…