Recent Advances in Google Real-Time HMM-Driven Unit Selection Synthesizer

  title={Recent Advances in Google Real-Time HMM-Driven Unit Selection Synthesizer},
  author={X. Gonzalvo and S. Tazari and Chun-an Chan and Markus Becker and Alexander Gutkin and Hanna Sil{\'e}n},
This paper presents advances in Google’s hidden Markov model (HMM)-driven unit selection speech synthesis system. We describe several improvements to the run-time system; these include minimal latency, high-quality and fast refresh cycle for new voices. Traditionally unit selection synthesizers are limited in terms of the amount of data they can handle and the real applications they are built for. That is even more critical for reallife large-scale applications where high-quality is expected… Expand
44 Citations
Siri On-Device Deep Learning-Guided Unit Selection Text-to-Speech System
  • 31
Master thesis : Automatic Multispeaker Voice Cloning
  • Highly Influenced
  • PDF
Streaming End-to-end Speech Recognition for Mobile Devices
  • 197
  • PDF
PPSpeech: Phrase based Parallel End-to-End TTS System
  • 1
  • PDF
Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
  • 154
  • PDF
Deep Voice 3: 2000-Speaker Neural Text-to-Speech
  • 144
  • PDF


Unit selection in a concatenative speech synthesis system using a large speech database
  • Andrew J. Hunt, A. Black
  • Computer Science
  • 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
  • 1996
  • 1,314
  • PDF
Local minimum generation error criterion for hybrid HMM speech synthesis
  • 10
  • PDF
Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis
  • 783
  • PDF
Phrase splicing and variable substitution using the IBM trainable speech synthesis system
  • 29
The USTC and iFlytek Speech Synthesis Systems for Blizzard Challenge 2007
  • 58
  • Highly Influential
  • PDF
Admissible stopping in viterbi beam search for unit selection in concatenative speech synthesis
  • 11
  • PDF
Towards High-Quality Next-Generation Text-to-Speech Synthesis: A Multidomain Approach by Automatic Domain Classification
  • 39
  • PDF
A Hidden Semi-Markov Model-Based Speech Synthesis System
  • 236
A perspective on the next challenges for TTS research
  • 33
  • PDF