← Search

Masanari Ohi

2 accepted papers

2025

HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

ICLR 2025poster

Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) mod- els using residual vector quantization (RVQ). However, long-fo…

2024

Likelihood-based Mitigation of Evaluation Bias in Large Language Models

ACL 2024findings

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics.However, the likelihood, a measure of LLM’s plausibility for a sentence, can vary due to superficial differences in sentences, such as word order and sentence structure.It is therefore pos…