Search Results for author:
Found 13 papers, 2 papers with code
DiarizationLM: Speaker Diarization Post-Processing with Large Language Models
In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
On Robustness to Missing Video for Audiovisual Speech Recognition
Multi-modal models need to be robust: missing video frames should not degrade the performance of an audiovisual model to be worse than that of a single-modality audio-only model.
Towards Word-Level End-to-End Neural Speaker Diarization with Auxiliary Network
Whether it is the conventional modularized approach or the more recent end-to-end neural diarization (EEND), an additional automatic speech recognition (ASR) model and an orchestration algorithm are required to associate the speaker labels with recognized words.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
USM-SCD: Multilingual Speaker Change Detection Based on Large Pretrained Foundation Models
We show that the USM-SCD model can achieve more than 75% average speaker change detection F1 score across a test set that consists of data from 96 languages.
Conformers are All You Need for Visual Speech Recognition
We achieve a new state-of-the-art of 12. 8% WER for visual speech recognition on the TED LRS3 dataset, which rivals the performance of audio-only models from just four years ago.
Ranked #1 on
Lipreading
on LRS3-TED
(using extra training data)
End-to-End Multi-Person Audio/Visual Automatic Speech Recognition
Traditionally, audio-visual automatic speech recognition has been studied under the assumption that the speaking face on the visual signal is the face matching the audio.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Recurrent Neural Network Transducer for Audio-Visual Speech Recognition
This work presents a large-scale audio-visual speech recognition system based on a recurrent neural network transducer (RNN-T) architecture.
Ranked #7 on
Audio-Visual Speech Recognition
on LRS3-TED
(using extra training data)
A comparison of end-to-end models for long-form speech recognition
In this paper, we both investigate and improve the performance of end-to-end models on long-form transcription.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Adversarial Training for Multilingual Acoustic Modeling
In this work, we apply the domain adversarial network to encourage the shared layers of a multilingual model to learn language-invariant features.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Neural Language Modeling with Visual Features
We report analysis that provides insights into why our multimodal language model improves upon a standard RNN language model.
Large-Scale Visual Speech Recognition
To achieve this, we constructed the largest existing visual speech recognition dataset, consisting of pairs of text and video clips of faces speaking (3, 886 hours of video).
Ranked #16 on
Lipreading
on LRS3-TED
(using extra training data)
Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition
Recurrent neural network (RNN) language models (LMs) and Long Short Term Memory (LSTM) LMs, a variant of RNN LMs, have been shown to outperform traditional N-gram LMs on speech recognition tasks.
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition
We present results that show it is possible to build a competitive, greatly simplified, large vocabulary continuous speech recognition system with whole words as acoustic units.
