conftrace_
← Topics

Speech & Audio

6,389 papers (14 classified directly here)

Subtopics

Recognition (3,347) Analysis (1,941) Synthesis (1,901) Processing (28)

Papers per year

5
2
704
360
'10
'15
'20
'25

Papers (including subtopics)

Characterizing Therapist's Speaking Style in Relation to Empathy in Psychotherapy INTERSPEECH 2022
Hierarchical Attention Network for Evaluating Therapist Empathy in Counseling Session INTERSPEECH 2022
Context-aware Multimodal Fusion for Emotion Recognition INTERSPEECH 2022
Unsupervised Instance Discriminative Learning for Depression Detection from Speech Signals INTERSPEECH 2022
How do our eyebrows respond to masks and whispering? The case of Persians INTERSPEECH 2022
State & Trait Measurement from Nonverbal Vocalizations: A Multi-Task Joint Learning Approach INTERSPEECH 2022
Accelerating Inference and Language Model Fusion of Recurrent Neural Network Transducers via End-to-End 4-bit Quantization INTERSPEECH 2022
Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognition INTERSPEECH 2022
Bring dialogue-context into RNN-T for streaming ASR INTERSPEECH 2022
Efficient Training of Neural Transducer for Speech Recognition INTERSPEECH 2022
Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition INTERSPEECH 2022
Pruned RNN-T for fast, memory-efficient ASR training INTERSPEECH 2022
Deep Sparse Conformer for Speech Recognition INTERSPEECH 2022
Chain-based Discriminative Autoencoders for Speech Recognition INTERSPEECH 2022
Streaming parallel transducer beam search with fast slow cascaded encoders INTERSPEECH 2022
Self-regularised Minimum Latency Training for Streaming Transformer-based Speech Recognition INTERSPEECH 2022
On the Prediction Network Architecture in RNN-T for ASR INTERSPEECH 2022
Minimum latency training of sequence transducers for streaming end-to-end speech recognition INTERSPEECH 2022
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR INTERSPEECH 2022
Attention Enhanced Citrinet for Speech Recognition INTERSPEECH 2022
Simple and Effective Zero-shot Cross-lingual Phoneme Recognition INTERSPEECH 2022
Robust Self-Supervised Audio-Visual Speech Recognition INTERSPEECH 2022
Speech Sequence Embeddings using Nearest Neighbors Contrastive Learning INTERSPEECH 2022
Towards Green ASR: Lossless 4-bit Quantization of a Hybrid TDNN System on the 300-hr Swithboard Corpus INTERSPEECH 2022
Finer-grained Modeling units-based Meta-Learning for Low-resource Tibetan Speech Recognition INTERSPEECH 2022