Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"speech": models, code, and papers

FastSpeech 2: Fast and High-Quality End-to-End Text to Speech

Jun 09, 2020
Yi Ren, Chenxu Hu, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Advanced text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs during training and use predicted values during inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of full end-to-end training and even faster inference than FastSpeech. Experimental results show that 1) FastSpeech 2 and 2s outperform FastSpeech in voice quality with much simplified training pipeline and reduced training time; 2) FastSpeech 2 and 2s can match the voice quality of autoregressive models while enjoying much faster inference speed.


  Access Paper or Ask Questions

FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech

Jun 08, 2020
Yi Ren, Chenxu Hu, Tao Qin, Sheng Zhao, Zhou Zhao, Tie-Yan Liu

Advanced text-to-speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is complicated, 2) the duration extracted from the teacher model is not accurate enough, and the target mel-spectrograms distilled from teacher model suffer from information loss due to data simplification, both of which limit the voice quality. In this paper, we propose FastSpeech 2, which addresses the issues in FastSpeech and better solves the one-to-many mapping problem in TTS by 1) directly training the model with ground-truth target instead of the simplified output from teacher, and 2) introducing more variation information of speech (e.g., pitch, energy and more accurate duration) as conditional inputs. Specifically, we extract duration, pitch and energy from speech waveform and directly take them as conditional inputs during training and use predicted values during inference. We further design FastSpeech 2s, which is the first attempt to directly generate speech waveform from text in parallel, enjoying the benefit of full end-to-end training and even faster inference than FastSpeech. Experimental results show that 1) FastSpeech 2 and 2s outperform FastSpeech in voice quality with much simplified training pipeline and reduced training time; 2) FastSpeech 2 and 2s can match the voice quality of autoregressive models while enjoying much faster inference speed.


  Access Paper or Ask Questions

Deep Learning for Distant Speech Recognition

Dec 17, 2017
Mirco Ravanelli

Deep learning is an emerging technology that is considered one of the most promising directions for reaching higher levels of artificial intelligence. Among the other achievements, building computers that understand speech represents a crucial leap towards intelligent machines. Despite the great efforts of the past decades, however, a natural and robust human-machine speech interaction still appears to be out of reach, especially when users interact with a distant microphone in noisy and reverberant environments. The latter disturbances severely hamper the intelligibility of a speech signal, making Distant Speech Recognition (DSR) one of the major open challenges in the field. This thesis addresses the latter scenario and proposes some novel techniques, architectures, and algorithms to improve the robustness of distant-talking acoustic models. We first elaborate on methodologies for realistic data contamination, with a particular emphasis on DNN training with simulated data. We then investigate on approaches for better exploiting speech contexts, proposing some original methodologies for both feed-forward and recurrent neural networks. Lastly, inspired by the idea that cooperation across different DNNs could be the key for counteracting the harmful effects of noise and reverberation, we propose a novel deep learning paradigm called network of deep neural networks. The analysis of the original concepts were based on extensive experimental validations conducted on both real and simulated data, considering different corpora, microphone configurations, environments, noisy conditions, and ASR tasks.

* PhD Thesis Unitn, 2017 

  Access Paper or Ask Questions

EditSpeech: A Text Based Speech Editing System Using Partial Inference and Bidirectional Fusion

Jul 04, 2021
Daxin Tan, Liqun Deng, Yu Ting Yeung, Xin Jiang, Xiao Chen, Tan Lee

This paper presents the design, implementation and evaluation of a speech editing system, named EditSpeech, which allows a user to perform deletion, insertion and replacement of words in a given speech utterance, without causing audible degradation in speech quality and naturalness. The EditSpeech system is developed upon a neural text-to-speech (NTTS) synthesis framework. Partial inference and bidirectional fusion are proposed to effectively incorporate the contextual information related to the edited region and achieve smooth transition at both left and right boundaries. Distortion introduced to the unmodified parts of the utterance is alleviated. The EditSpeech system is developed and evaluated on English and Chinese in multi-speaker scenarios. Objective and subjective evaluation demonstrate that EditSpeech outperforms a few baseline systems in terms of low spectral distortion and preferred speech quality. Audio samples are available online for demonstration https://daxintan-cuhk.github.io/EditSpeech/ .


  Access Paper or Ask Questions

Multilingual Speech Translation with Unified Transformer: Huawei Noah's Ark Lab at IWSLT 2021

Jun 22, 2021
Xingshan Zeng, Liangyou Li, Qun Liu

This paper describes the system submitted to the IWSLT 2021 Multilingual Speech Translation (MultiST) task from Huawei Noah's Ark Lab. We use a unified transformer architecture for our MultiST model, so that the data from different modalities (i.e., speech and text) and different tasks (i.e., Speech Recognition, Machine Translation, and Speech Translation) can be exploited to enhance the model's ability. Specifically, speech and text inputs are firstly fed to different feature extractors to extract acoustic and textual features, respectively. Then, these features are processed by a shared encoder--decoder architecture. We apply several training techniques to improve the performance, including multi-task learning, task-level curriculum learning, data augmentation, etc. Our final system achieves significantly better results than bilingual baselines on supervised language pairs and yields reasonable results on zero-shot language pairs.

* IWSLT 2021 

  Access Paper or Ask Questions

RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer

Jun 09, 2021
Xingshan Zeng, Liangyou Li, Qun Liu

End-to-end simultaneous speech translation (SST), which directly translates speech in one language into text in another language in real-time, is useful in many scenarios but has not been fully investigated. In this work, we propose RealTranS, an end-to-end model for SST. To bridge the modality gap between speech and text, RealTranS gradually downsamples the input speech with interleaved convolution and unidirectional Transformer layers for acoustic modeling, and then maps speech features into text space with a weighted-shrinking operation and a semantic encoder. Besides, to improve the model performance in simultaneous scenarios, we propose a blank penalty to enhance the shrinking quality and a Wait-K-Stride-N strategy to allow local reranking during decoding. Experiments on public and widely-used datasets show that RealTranS with the Wait-K-Stride-N strategy outperforms prior end-to-end models as well as cascaded models in diverse latency settings.

* Accepted by ACL2021 Findings 

  Access Paper or Ask Questions

Statistical Parametric Speech Synthesis Using Bottleneck Representation From Sequence Auto-encoder

Jun 19, 2016
Sivanand Achanta, KNRK Raju Alluri, Suryakanth V Gangashetty

In this paper, we describe a statistical parametric speech synthesis approach with unit-level acoustic representation. In conventional deep neural network based speech synthesis, the input text features are repeated for the entire duration of phoneme for mapping text and speech parameters. This mapping is learnt at the frame-level which is the de-facto acoustic representation. However much of this computational requirement can be drastically reduced if every unit can be represented with a fixed-dimensional representation. Using recurrent neural network based auto-encoder, we show that it is indeed possible to map units of varying duration to a single vector. We then use this acoustic representation at unit-level to synthesize speech using deep neural network based statistical parametric speech synthesis technique. Results show that the proposed approach is able to synthesize at the same quality as the conventional frame based approach at a highly reduced computational cost.

* 5 pages (with references) 

  Access Paper or Ask Questions

Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks

Oct 14, 2021
Sangeeta Srivastava, Yun Wang, Andros Tjandra, Anurag Kumar, Chunxi Liu, Kritika Singh, Yatharth Saraf

Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have comprehensively analyzed audio representation learning for non-speech audio tasks. In this paper, we propose a self-supervised audio representation learning method and apply it to a variety of downstream non-speech audio tasks. We combine the well-known wav2vec 2.0 framework, which has shown success in self-supervised learning for speech tasks, with parameter-efficient conformer architectures. On the AudioSet benchmark, we achieve a mean average precision (mAP) score of 0.415, which is a new state-of-the-art on this dataset through audio-only self-supervised learning. Our fine-tuned conformers also surpass or match the performance of previous systems pre-trained in a supervised way on several downstream tasks. We further discuss the important design considerations for both pre-training and fine-tuning.

* 4 pages. Submitted to ICASSP in Oct 2021 

  Access Paper or Ask Questions

Cross-lingual hate speech detection based on multilingual domain-specific word embeddings

Apr 30, 2021
Aymé Arango, Jorge Pérez, Barbara Poblete

Automatic hate speech detection in online social networks is an important open problem in Natural Language Processing (NLP). Hate speech is a multidimensional issue, strongly dependant on language and cultural factors. Despite its relevance, research on this topic has been almost exclusively devoted to English. Most supervised learning resources, such as labeled datasets and NLP tools, have been created for this same language. Considering that a large portion of users worldwide speak in languages other than English, there is an important need for creating efficient approaches for multilingual hate speech detection. In this work we propose to address the problem of multilingual hate speech detection from the perspective of transfer learning. Our goal is to determine if knowledge from one particular language can be used to classify other language, and to determine effective ways to achieve this. We propose a hate specific data representation and evaluate its effectiveness against general-purpose universal representations most of which, unlike our proposed model, have been trained on massive amounts of data. We focus on a cross-lingual setting, in which one needs to classify hate speech in one language without having access to any labeled data for that language. We show that the use of our simple yet specific multilingual hate representations improves classification results. We explain this with a qualitative analysis showing that our specific representation is able to capture some common patterns in how hate speech presents itself in different languages. Our proposal constitutes, to the best of our knowledge, the first attempt for constructing multilingual specific-task representations. Despite its simplicity, our model outperformed the previous approaches for most of the experimental setups. Our findings can orient future solutions toward the use of domain-specific representations.


  Access Paper or Ask Questions

<<
82
83
84
85
86
87
88
89
90
91
92
93
94
>>