← Search

Cheng-I Jeff Lai

2 accepted papers

2023

Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences

ICASSP 2023accepted

Past work on unsupervised parsing is constrained to written form. In this paper, we present the first study on unsupervised spoken constituency parsing given unlabeled spoken sentences and unpaired textual data. The goal is to determine the spoken sentences’ hierarchical syntactic structure in the f…

Cited by 0SourceScholar
2022

On the Interplay between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesis

ICASSP 2022accepted

Are end-to-end text-to-speech (TTS) models over-parametrized? To what extent can these models be pruned, and what happens to their synthesis capabilities? This work serves as a starting point to explore pruning both spectrogram prediction networks and vocoders. We thoroughly investigate the tradeoff…

Cited by 0SourceScholar