Pervasive Artificial Intelligence Research (PAIR) Labs

Natural Language Application

Pervasive Artificial Intelligence Research (PAIR) Labs

Natural Language Application

Academia Sinica – Professor Hsin-Min Wang

Research :

Deep Intelligence Based Spoken Language Processing

Core Technologies

Our research goal is to develop methods for analyzing, extracting, recognizing, indexing, and retrieving information from audio data, with special emphasis on speech and music. Currently, we focus on automatic speech recognition, voice conversion, text-to-speech synthesis, speaker recognition, speaker diarization, and spoken langauge identification.

Applications

1. human-machine speech interface
2. electronic audiobook

Technology Transfer

1. voice conversion

2. Mandarin Chinese ASR

3. speaker recognition

4. speaker diarization

Technologies with Potential for Technology Transfer or Industry-Academia Collaboration

1. Taiwanese Southern-Min ASR
2. Mandarin-Taiwanese code-switching ASR

Proposal for Industry-Academia Collaboration

speaking aids for patients with impaired pronunciation