Picture for Md Asif Jalal

Md Asif Jalal

Locality enhanced dynamic biasing and sampling strategies for contextual ASR

Add code
Jan 23, 2024
Viaarxiv icon

Consistency Based Unsupervised Self-training For ASR Personalisation

Jan 22, 2024
Viaarxiv icon

On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer

Jul 25, 2023
Figure 1 for On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
Figure 2 for On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
Figure 3 for On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
Figure 4 for On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer
Viaarxiv icon

Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition

Add code
Jun 30, 2023
Figure 1 for Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition
Figure 2 for Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition
Figure 3 for Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition
Figure 4 for Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition
Viaarxiv icon

Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation

Mar 01, 2023
Figure 1 for Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
Figure 2 for Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
Figure 3 for Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
Figure 4 for Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation
Viaarxiv icon

Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification

Nov 03, 2022
Figure 1 for Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification
Figure 2 for Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification
Figure 3 for Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification
Figure 4 for Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification
Viaarxiv icon

Probing Statistical Representations For End-To-End ASR

Nov 03, 2022
Figure 1 for Probing Statistical Representations For End-To-End ASR
Figure 2 for Probing Statistical Representations For End-To-End ASR
Figure 3 for Probing Statistical Representations For End-To-End ASR
Figure 4 for Probing Statistical Representations For End-To-End ASR
Viaarxiv icon

A cross-corpus study on speech emotion recognition

Add code
Jul 05, 2022
Figure 1 for A cross-corpus study on speech emotion recognition
Figure 2 for A cross-corpus study on speech emotion recognition
Figure 3 for A cross-corpus study on speech emotion recognition
Figure 4 for A cross-corpus study on speech emotion recognition
Viaarxiv icon

Insights on Neural Representations for End-to-End Speech Recognition

May 19, 2022
Figure 1 for Insights on Neural Representations for End-to-End Speech Recognition
Figure 2 for Insights on Neural Representations for End-to-End Speech Recognition
Figure 3 for Insights on Neural Representations for End-to-End Speech Recognition
Figure 4 for Insights on Neural Representations for End-to-End Speech Recognition
Viaarxiv icon

Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion

Add code
Feb 22, 2021
Figure 1 for Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion
Figure 2 for Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion
Figure 3 for Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion
Figure 4 for Investigating Deep Neural Structures and their Interpretability in the Domain of Voice Conversion
Viaarxiv icon