The aligner: text to speech alignment using Markov models and a pronunciation dictionary

By David Talkin, Colin W. Wightman. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Tao Qin
3. Ye Jia
4. Yu Zhang
5. Tie-Yan Liu
6. Frank K. Soong
7. Yi Ren
8. Zhaoxi Mu

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, methodology): “The works leveraging external alignment tools [381, 91, 226, 189] can be divided into several categories according to the used alignment tools: 1) Encoder-decoder attention: FastSpeech [284] obtains the duration label from the attention alignments of an autoregressive acoustic model.”
• Parallel Tacotron: Non-Autoregressive and Controllable TTS (2020, methodology): “We assume that groundtruth phoneme durations are provided by an external aligner, such as hidden Markov model (HMM)-based one [37].”
• Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration Modeling (2020, methodology): “In our work, target durations are extracted by an external, flatstart trained, speaker-dependent HMM-based aligner with a lexicon (Talkin & Wightman, 1994).”
• The original ToBI system and the evolution of the ToBI framework (2003, methodology): “At many such sites, a firstpass Phones-tier labelling is done automatically using an alignment program, such as Aligner (Wightman and Talkin 1994) or some other similar HMM-based automatic transcription alignment system.”
• Review of end-to-end speech synthesis technology based on deep learning (2021, methodology): “For example, TalkNet [12] uses the CTC-based automatic speech recognition (ASR) model Quartznet [111], FastSpeech 2 [174] uses the forcedalignment tool MFA toolkit [135], DurIAN [243] uses a external alignment model [51, 252], RobuTrans [119] uses speech recognition tools, Parallel Tacotron [49] and”