Neural net word representations for phrase-break prediction without a part of speech tagger

No abstract is available for this paper.

• Publication year

  2014

• Venue

  IEEE International Conference on Acoustics, Speech, and Signal Processing

• Publication date

  2014-05-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ICASSP.2014.6854070
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Unsupervised learning for text-to-speech synthesis

  2013influential reference
• Multi-distribution deep belief network for speech synthesis

  2013cited by this paper
• Modeling Spectral Envelopes Using Restricted Boltzmann Machines and Deep Belief Networks for Statistical Parametric Speech Synthesis

  2013cited by this paper
• Statistical parametric speech synthesis using deep neural networks

  2013cited by this paper
• Natural Language Processing (Almost) from Scratch

  2011cited by this paper
• Unsupervised Continuous-Valued Word Features for Phrase-Break Prediction without a Part-of-Speech Tagger

  2011influential reference
• Understanding the difficulty of training deep feedforward neural networks

  2010cited by this paper
• Improved neural network based language modelling and adaptation

  2010cited by this paper
• A unified architecture for natural language processing: deep neural networks with multitask learning

  2008cited by this paper
• Stochastic and syntactic techniques for predicting phrase breaks

  2007cited by this paper
• Continuous space language models

  2007cited by this paper
• A Neural Probabilistic Language Model

  2003influential reference
• Connectionist language modeling for large vocabulary continuous speech recognition

  2002cited by this paper
• Predicting phrase breaks with memory-based learning

  2001cited by this paper
• TnT – A Statistical Part-of-Speech Tagger

  2000cited by this paper
• Self-organizing letter code-book for text-to-phoneme neural network model

  2000influential reference
• Gradient-based learning applied to document recognition

  1998cited by this paper
• Multitask Learning

  1997influential reference
• Assigning phrase breaks from part-of-speech sequences

  1997cited by this paper
• Working with speech : perspectives on research into the Lancaster/IBM Spoken English Corpus

  1996cited by this paper
• MARSEC: A Machine-Readable Spoken English Corpus

  1993cited by this paper

• An Investigation of Phrase Break Prediction in an End-to-End TTS System

  2023cites this paper
• Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

  2021cites this paper
• Phrase break prediction with bidirectional encoder representations in Japanese text-to-speech synthesis

  2021cites this paper
• Submission from CMU for Blizzard Challenge 2018

  2018cites this paper
• Phonologically Aware BiLSTM Model for Mongolian Phrase Break Prediction with Attention Mechanism

  2018cites this paper
• Improving Mongolian Phrase Break Prediction by Using Syllable and Morphological Embeddings with BiLSTM Model

  2018cites this paper
• Automatic phrase break and sentence stress prediction in English with RNN

  2018cites this paper
• Global Syllable Vectors for Building TTS Front-End with Deep Learning

  2017influential citation
• Learning Word Vector Representations Based on Acoustic Counts

  2017cites this paper
• Improving an Italian TTS System : Voice Based Rules for Word Boundaries' Phenomena

  2017cites this paper
• Phrase Break Prediction for Long-Form Reading TTS: Exploiting Text Structure Information

  2017cites this paper
• Phoneme Embedding and its Application to Speech Driven Talking Avatar Synthesis

  2016cites this paper
• Syllable-Level Representations of Suprasegmental Features for DNN-Based Text-to-Speech Synthesis

  2016cites this paper
• Parallel and cascaded deep neural networks for text-to-speech synthesis

  2016cites this paper
• An Investigation of Recurrent Neural Network Architectures Using Word Embeddings for Phrase Break Prediction

  2016cites this paper
• Prosodic Break Prediction with RNNs

  2016cites this paper
• Symbolic Modeling of Prosody: From Linguistics to Statistics

  2015cites this paper
• Word embedding for recurrent neural network based TTS synthesis

  2015cites this paper
• Sentence-level control vectors for deep neural network speech synthesis

  2015cites this paper