Search Results for author:
Found 13 papers, 8 papers with code
StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion
Using classifier-free guidance, StyleTTS-ZS achieves high similarity to the reference speaker in the style diffusion process.
Just ASR + LLM? A Study on Speech Large Language Models' Ability to Identify and Understand Speaker in Spoken Dialogue
However, after carefully examining Gaokao's questions, we find the correct answers to many questions can be inferred from the conversation transcript alone, i. e.\ without speaker segmentation and identification.
Style-Talker: Finetuning Audio Language Model and Style-Based Text-to-Speech Model for Fast Spoken Dialogue Generation
While the response speech is being played, the input speech undergoes ASR processing to extract the transcription and speaking style, serving as the context for the ensuing dialogue turn.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis
It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks.
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model
Transformers have revolutionized deep learning across various tasks, including audio representation learning, due to their powerful modeling capabilities.
Ranked #2 on
Keyword Spotting
on Google Speech Commands V2 35
(using extra training data)
Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separation
In this work, we replace transformers with Mamba, a selective state space model, for speech separation.
Listen, Chat, and Edit: Text-Guided Soundscape Modification for Enhanced Auditory Experience
In daily life, we encounter a variety of sounds, both desirable and undesirable, with limited control over their presence and volume.
Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation
In this study, we present a simple multi-channel framework for contrastive learning (MC-SimCLR) to encode 'what' and 'where' of spatial audios.
HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform
Subjective evaluations on LJSpeech show that our model significantly outperforms both iSTFTNet and HiFi-GAN, achieving ground-truth-level performance.
DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes
Lifelong audio feature extraction involves learning new sound classes incrementally, which is essential for adapting to new data distributions over time.
Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns.
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
In this paper, we work on a sound recognition system that continually incorporates new sound classes.
Compute and memory efficient universal sound source separation
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem.
Ranked #5 on
Speech Separation
on WHAMR!
