Picture for Murali Karthick Baskar

Murali Karthick Baskar

Speculative Speech Recognition by Audio-Prefixed Low-Rank Adaptation of Language Models

Add code
Jul 05, 2024
Viaarxiv icon

Speech Prefix-Tuning with RNNT Loss for Improving LLM Predictions

Add code
Jun 20, 2024
Viaarxiv icon

O-1: Self-training with Oracle and 1-best Hypothesis

Add code
Aug 14, 2023
Figure 1 for O-1: Self-training with Oracle and 1-best Hypothesis
Figure 2 for O-1: Self-training with Oracle and 1-best Hypothesis
Figure 3 for O-1: Self-training with Oracle and 1-best Hypothesis
Figure 4 for O-1: Self-training with Oracle and 1-best Hypothesis
Viaarxiv icon

Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss

Add code
Mar 10, 2023
Figure 1 for Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Figure 2 for Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Figure 3 for Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Figure 4 for Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-Sum Loss
Viaarxiv icon

Speaker adaptation for Wav2vec2 based dysarthric ASR

Add code
Apr 02, 2022
Figure 1 for Speaker adaptation for Wav2vec2 based dysarthric ASR
Figure 2 for Speaker adaptation for Wav2vec2 based dysarthric ASR
Figure 3 for Speaker adaptation for Wav2vec2 based dysarthric ASR
Figure 4 for Speaker adaptation for Wav2vec2 based dysarthric ASR
Viaarxiv icon

Ask2Mask: Guided Data Selection for Masked Speech Modeling

Add code
Feb 24, 2022
Figure 1 for Ask2Mask: Guided Data Selection for Masked Speech Modeling
Figure 2 for Ask2Mask: Guided Data Selection for Masked Speech Modeling
Figure 3 for Ask2Mask: Guided Data Selection for Masked Speech Modeling
Figure 4 for Ask2Mask: Guided Data Selection for Masked Speech Modeling
Viaarxiv icon

EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition

Add code
Apr 13, 2021
Figure 1 for EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Figure 2 for EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Figure 3 for EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Figure 4 for EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition
Viaarxiv icon

BUT Opensat 2019 Speech Recognition System

Add code
Jan 30, 2020
Figure 1 for BUT Opensat 2019 Speech Recognition System
Figure 2 for BUT Opensat 2019 Speech Recognition System
Figure 3 for BUT Opensat 2019 Speech Recognition System
Figure 4 for BUT Opensat 2019 Speech Recognition System
Viaarxiv icon

Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

Add code
Apr 30, 2019
Figure 1 for Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Figure 2 for Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Figure 3 for Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Figure 4 for Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text
Viaarxiv icon

Analysis of Multilingual Sequence-to-Sequence speech recognition systems

Add code
Nov 07, 2018
Figure 1 for Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Figure 2 for Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Figure 3 for Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Figure 4 for Analysis of Multilingual Sequence-to-Sequence speech recognition systems
Viaarxiv icon