Search Results for author:
Found 14 papers, 6 papers with code
BreezyVoice: Adapting TTS for Taiwanese Mandarin with Enhanced Polyphone Disambiguation -- Challenges and Insights
We present BreezyVoice, a Text-to-Speech (TTS) system specifically adapted for Taiwanese Mandarin, highlighting phonetic control abilities to address the unique challenges of polyphone disambiguation in the language.
Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations.
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
We present Dynamic-SUPERB Phase-2, an open and evolving benchmark for the comprehensive evaluation of instruction-based universal speech models.
Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models
Neural audio codec models are becoming increasingly important as they serve as tokenizers for audio, enabling efficient transmission or facilitating speech language modeling.
Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection
Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction.
Leveraging Joint Spectral and Spatial Learning with MAMBA for Multichannel Speech Enhancement
In multichannel speech enhancement, effectively capturing spatial and spectral information across different microphones is crucial for noise reduction.
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget
We examine critical factors in SSL that impact the budget, including model architecture, model size, and data size.
Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models
Warning: This paper may contain texts with uncomfortable content.
EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations
The neural codec model reduces speech data transmission delay and serves as the foundational tokenizer for speech language models (speech LMs).
Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models
Speech Integrated Large Language Models (SILLMs) combine large language models with speech perception to perform diverse tasks, such as emotion recognition to speaker verification, demonstrating universal audio understanding capability.
On the social bias of speech self-supervised models
We probe how various factors, such as model architecture, size, and training methodologies, influence the propagation of social bias within these models.
Emo-bias: A Large Scale Evaluation of Social Bias on Speech Emotion Recognition
The rapid growth of Speech Emotion Recognition (SER) has diverse global applications, from improving human-computer interactions to aiding mental health diagnostics.
Towards audio language modeling - an overview
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency.
Codec-SUPERB: An In-Depth Analysis of Sound Codec Models
The sound codec's dual roles in minimizing data transmission latency and serving as tokenizers underscore its critical importance.
