Andreas Stolcke

research

∙ 03/16/2022

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals

We propose a framework to modularize the training of neural language mod...

Scott Novotney, et al. ∙

research

∙ 02/23/2022

Improving fairness in speaker verification via Group-adapted Fusion Network

Modern speaker verification models use deep neural networks to encode ut...

Hua Shen, et al. ∙

research

∙ 02/22/2022

Contrastive-mixup learning for improved speaker verification

This paper proposes a novel formulation of prototypical loss with mixup ...

Xin Zhang, et al. ∙

research

∙ 02/17/2022

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition

In this work, we aim to enhance the system robustness of end-to-end auto...

Chao-Han Huck Yang, et al. ∙

research

∙ 02/07/2022

Self-supervised Speaker Recognition Training Using Human-Machine Dialogues

Speaker recognition, recognizing speaker identities based on voice alone...

Metehan Cekic, et al. ∙

research

∙ 02/02/2022

ASR-Aware End-to-end Neural Diarization

We present a Conformer-based end-to-end neural diarization (EEND) model ...

Aparna Khare, et al. ∙

research

∙ 02/02/2022

RescoreBERT: Discriminative Speech Recognition Rescoring with BERT

Second-pass rescoring is an important component in automatic speech reco...

Liyan Xu, et al. ∙

research

∙ 09/06/2021

Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets

Speaker identification typically involves three stages. First, a front-e...

Zhenning Tan, et al. ∙

research

∙ 06/18/2021

Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition

By implicitly recognizing a user based on his/her speech input, speaker ...

Ruirui Li, et al. ∙

research

∙ 06/15/2021

Graph-based Label Propagation for Semi-Supervised Speaker Identification

Speaker identification in the household scenario (e.g., for smart speake...

Long Chen, et al. ∙

research

∙ 06/14/2021

End-to-end Neural Diarization: From Transformer to Conformer

We propose a new end-to-end neural diarization (EEND) system that is bas...

Yi-Chieh Liu, et al. ∙

research

∙ 06/02/2021

Attention-based Contextual Language Model Adaptation for Speech Recognition

Language modeling (LM) for automatic speech recognition (ASR) does not u...

Richard Diehl Martinez, et al. ∙

research

∙ 05/14/2021

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End

Comprehending the overall intent of an utterance helps a listener recogn...

Swayambhu Nath Ray, et al. ∙

research

∙ 04/25/2021

Reranking Machine Translation Hypotheses with Structured and Web-based Language Models

In this paper, we investigate the use of linguistically motivated and co...

Wen Wang, et al. ∙

research

∙ 03/09/2021

Wav2vec-C: A Self-supervised Model for Speech Representation Learning

Wav2vec-C introduces a novel representation learning technique combining...

Samik Sadhu, et al. ∙

research

∙ 02/15/2021

Personalization Strategies for End-to-End Speech Recognition Systems

The recognition of personalized content, such as contact names, remains ...

Aditya Gourav, et al. ∙

research

∙ 02/12/2021

Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding

Spoken language understanding (SLU) systems extract transcriptions, as w...

Milind Rao, et al. ∙

research

∙ 12/14/2020

REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling

Accents mismatching is a critical problem for end-to-end ASR. This paper...

Hu Hu, et al. ∙

research

∙ 11/05/2020

BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers

We present a novel online end-to-end neural diarization system, BW-EDA-E...

Eunjung Han, et al. ∙

research

∙ 11/03/2020

DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs

Several advances have been made recently towards handling overlapping sp...

Desh Raj, et al. ∙

research

∙ 07/27/2020

Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition

In this work, we propose a novel and efficient minimum word error rate (...

Jinxi Guo, et al. ∙

research

∙ 10/24/2019

Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm

Speaker diarization based on bottom-up clustering of speech segments by ...

Andreas Stolcke, et al. ∙

research

∙ 10/24/2019

Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings

Involvement hot spots have been proposed as a useful concept for meeting...

Dave Makhervaks, et al. ∙

research

∙ 09/17/2019

DOVER: A Method for Combining Diarization Outputs

Speech recognition and other natural language tasks have long benefited ...

Andreas Stolcke, et al. ∙

research

∙ 05/03/2019

Meeting Transcription Using Virtual Microphone Arrays

We describe a system that generates speaker-annotated transcripts of mee...

Takuya Yoshioka, et al. ∙

research

∙ 08/29/2017

Comparing Human and Machine Errors in Conversational Speech Transcription

Recent work in automatic recognition of conversational telephone speech ...

Andreas Stolcke, et al. ∙

Andreas Stolcke

Featured Co-authors

Shinji Watanabe

Long Chen

Xin Zhang

Zhuo Chen

Di He

Takuya Yoshioka

Michael Zeng

Sanjeev Khudanpur

Wen Wang

Chao-Han Huck Yang

Ariya Rastrow

CUE Vectors: Modular Training of Language Models Conditioned on Diverse Contextual Signals

Improving fairness in speaker verification via Group-adapted Fusion Network

Contrastive-mixup learning for improved speaker verification

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition

Self-supervised Speaker Recognition Training Using Human-Machine Dialogues

ASR-Aware End-to-end Neural Diarization

RescoreBERT: Discriminative Speech Recognition Rescoring with BERT

Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets

Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition

Graph-based Label Propagation for Semi-Supervised Speaker Identification

End-to-end Neural Diarization: From Transformer to Conformer

Attention-based Contextual Language Model Adaptation for Speech Recognition

Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End

Reranking Machine Translation Hypotheses with Structured and Web-based Language Models

Wav2vec-C: A Self-supervised Model for Speech Representation Learning

Personalization Strategies for End-to-End Speech Recognition Systems

Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding

REDAT: Accent-Invariant Representation for End-to-End ASR by Domain Adversarial Training with Relabeling

BW-EDA-EEND: Streaming End-to-End Neural Speaker Diarization for a Variable Number of Speakers

DOVER-Lap: A Method for Combining Overlap-aware Diarization Outputs

Efficient minimum word error rate training of RNN-Transducer for end-to-end speech recognition

Improving Diarization Robustness using Diversification, Randomization and the DOVER Algorithm

Combining Acoustics, Content and Interaction Features to Find Hot Spots in Meetings

DOVER: A Method for Combining Diarization Outputs

Meeting Transcription Using Virtual Microphone Arrays

Comparing Human and Machine Errors in Conversational Speech Transcription