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

Many-to-Many Voice Transformer Network

May 18, 2020
Hirokazu Kameoka, Wen-Chin Huang, Kou Tanaka, Takuhiro Kaneko, Nobukatsu Hojo, Tomoki Toda

This paper proposes a voice conversion (VC) method based on a sequence-to-sequence (S2S) learning framework, which makes it possible to simultaneously convert the voice characteristics, pitch contour and duration of input speech. We previously proposed an S2S-based VC method using a transformer network architecture, which we call the "voice transformer network (VTN)". While the original VTN is designed to learn only a mapping of speech feature sequences from one domain into another, we extend it so that it can simultaneously learn mappings among multiple domains using only a single model. This allows the model to fully utilize available training data collected from multiple domains by capturing common latent features that can be shared across different domains. On top of this model, we further propose incorporating a training loss called the "identity mapping loss", to ensure that the input feature sequence will remain unchanged when it already belongs to the target domain. Using this particular loss for model training has been found to be extremely effective in improving the performance of the model at test time. We conducted speaker identity conversion experiments and showed that model obtained higher sound quality and speaker similarity than baseline methods.

  Access Paper or Ask Questions

Scalable Factorized Hierarchical Variational Autoencoder Training

Jun 15, 2018
Wei-Ning Hsu, James Glass

Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations. Among them, a factorized hierarchical variational autoencoder (FHVAE) is a variational inference-based model that formulates a hierarchical generative process for sequential data. Specifically, an FHVAE model can learn disentangled and interpretable representations, which have been proven useful for numerous speech applications, such as speaker verification, robust speech recognition, and voice conversion. However, as we will elaborate in this paper, the training algorithm proposed in the original paper is not scalable to datasets of thousands of hours, which makes this model less applicable on a larger scale. After identifying limitations in terms of runtime, memory, and hyperparameter optimization, we propose a hierarchical sampling training algorithm to address all three issues. Our proposed method is evaluated comprehensively on a wide variety of datasets, ranging from 3 to 1,000 hours and involving different types of generating factors, such as recording conditions and noise types. In addition, we also present a new visualization method for qualitatively evaluating the performance with respect to the interpretability and disentanglement. Models trained with our proposed algorithm demonstrate the desired characteristics on all the datasets.

* Interspeech 2018 

  Access Paper or Ask Questions

End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system

Feb 18, 2022
Zhengyi Zhang, Pan Zhou

End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse performance on utterances containing infrequent proper nouns. In this work, we propose to add a contextual bias attention (CBA) module to attention based encoder decoder (AED) model to improve its ability of recognizing the contextual phrases. Specifically, CBA utilizes the context vector of source attention in decoder to attend to a specific bias embedding. Jointly learned with the basic AED parameters, CBA can tell the model when and where to bias its output probability distribution. At inference stage, a list of bias phrases is preloaded and we adapt the posterior distributions of both CTC and attention decoder according to the attended bias phrase of CBA. We evaluate the proposed method on GigaSpeech and achieve a consistent relative improvement on recall rate of bias phrases ranging from 15% to 28% compared to the baseline model. Meanwhile, our method shows a strong anti-bias ability as the performance on general tests only degrades 1.7% even 2,000 bias phrases are present.

* 5 pages, 5 tabels, 1 figure 

  Access Paper or Ask Questions

Unsupervised Multimodal Word Discovery based on Double Articulation Analysis with Co-occurrence cues

Jan 18, 2022
Akira Taniguchi, Hiroaki Murakami, Ryo Ozaki, Tadahiro Taniguchi

Human infants acquire their verbal lexicon from minimal prior knowledge of language based on the statistical properties of phonological distributions and the co-occurrence of other sensory stimuli. In this study, we propose a novel fully unsupervised learning method discovering speech units by utilizing phonological information as a distributional cue and object information as a co-occurrence cue. The proposed method can not only (1) acquire words and phonemes from speech signals using unsupervised learning, but can also (2) utilize object information based on multiple modalities (i.e., vision, tactile, and auditory) simultaneously. The proposed method is based on the Nonparametric Bayesian Double Articulation Analyzer (NPB-DAA) discovering phonemes and words from phonological features, and Multimodal Latent Dirichlet Allocation (MLDA) categorizing multimodal information obtained from objects. In the experiment, the proposed method showed higher word discovery performance than the baseline methods. In particular, words that expressed the characteristics of the object (i.e., words corresponding to nouns and adjectives) were segmented accurately. Furthermore, we examined how learning performance is affected by differences in the importance of linguistic information. When the weight of the word modality was increased, the performance was further improved compared to the fixed condition.

  Access Paper or Ask Questions

Meta-Voice: Fast few-shot style transfer for expressive voice cloning using meta learning

Nov 14, 2021
Songxiang Liu, Dan Su, Dong Yu

The task of few-shot style transfer for voice cloning in text-to-speech (TTS) synthesis aims at transferring speaking styles of an arbitrary source speaker to a target speaker's voice using very limited amount of neutral data. This is a very challenging task since the learning algorithm needs to deal with few-shot voice cloning and speaker-prosody disentanglement at the same time. Accelerating the adaptation process for a new target speaker is of importance in real-world applications, but even more challenging. In this paper, we approach to the hard fast few-shot style transfer for voice cloning task using meta learning. We investigate the model-agnostic meta-learning (MAML) algorithm and meta-transfer a pre-trained multi-speaker and multi-prosody base TTS model to be highly sensitive for adaptation with few samples. Domain adversarial training mechanism and orthogonal constraint are adopted to disentangle speaker and prosody representations for effective cross-speaker style transfer. Experimental results show that the proposed approach is able to conduct fast voice cloning using only 5 samples (around 12 second speech data) from a target speaker, with only 100 adaptation steps. Audio samples are available online.

* Pre-print technical report, 6 pages, 6 figures 

  Access Paper or Ask Questions

Multilingual transfer of acoustic word embeddings improves when training on languages related to the target zero-resource language

Jun 24, 2021
Christiaan Jacobs, Herman Kamper

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no labelled data is available in the target language. The current best approach uses transfer learning: a single supervised multilingual model is trained using labelled data from multiple well-resourced languages and then applied to a target zero-resource language (without fine-tuning). However, it is still unclear how the specific choice of training languages affect downstream performance. Concretely, here we ask whether it is beneficial to use training languages related to the target. Using data from eleven languages spoken in Southern Africa, we experiment with adding data from different language families while controlling for the amount of data per language. In word discrimination and query-by-example search evaluations, we show that training on languages from the same family gives large improvements. Through finer-grained analysis, we show that training on even just a single related language gives the largest gain. We also find that adding data from unrelated languages generally doesn't hurt performance.

* Accepted to Interspeech 2021 

  Access Paper or Ask Questions

Overcoming Domain Mismatch in Low Resource Sequence-to-Sequence ASR Models using Hybrid Generated Pseudotranscripts

Jun 14, 2021
Chak-Fai Li, Francis Keith, William Hartmann, Matthew Snover, Owen Kimball

Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for seq2seq models than their hybrid counterparts. We examine corpora of five languages from the IARPA MATERIAL program where the transcribed data is conversational telephone speech (CTS) and evaluation data is broadcast news (BN). We show that there is a sizable initial gap in such a data condition between hybrid and seq2seq models, and the hybrid model is able to further improve through the use of additional language model (LM) data. We use an additional set of untranscribed data primarily in the BN domain for semisupervised training. In semisupervised training, a seed model trained on transcribed data generates hypothesized transcripts for unlabeled domain-matched data for further training. By using a hybrid model with an expanded language model for pseudotranscription, we are able to improve our seq2seq model from an average word error rate (WER) of 66.7% across all five languages to 29.0% WER. While this puts the seq2seq model at a competitive operating point, hybrid models are still able to use additional LM data to maintain an advantage.

* 5 pages 

  Access Paper or Ask Questions

Neuronal Sequence Models for Bayesian Online Inference

Apr 02, 2020
Sascha Frölich, Dimitrije Marković, Stefan J. Kiebel

Sequential neuronal activity underlies a wide range of processes in the brain. Neuroscientific evidence for neuronal sequences has been reported in domains as diverse as perception, motor control, speech, spatial navigation and memory. Consequently, different dynamical principles have been proposed as possible sequence-generating mechanisms. Combining experimental findings with computational concepts like the Bayesian brain hypothesis and predictive coding leads to the interesting possibility that predictive and inferential processes in the brain are grounded on generative processes which maintain a sequential structure. While probabilistic inference about ongoing sequences is a useful computational model for both the analysis of neuroscientific data and a wide range of problems in artificial recognition and motor control, research on the subject is relatively scarce and distributed over different fields in the neurosciences. Here we review key findings about neuronal sequences and relate these to the concept of online inference on sequences as a model of sensory-motor processing and recognition. We propose that describing sequential neuronal activity as an expression of probabilistic inference over sequences may lead to novel perspectives on brain function. Importantly, it is promising to translate the key idea of probabilistic inference on sequences to machine learning, in order to address challenges in the real-time recognition of speech and human motion.

  Access Paper or Ask Questions

Uncertainty in Structured Prediction

Feb 28, 2020
Andrey Malinin, Mark Gales

Uncertainty estimation is important for ensuring safety and robustness of AI systems, especially for high-risk applications. While much progress has recently been made in this area, most research has focused on un-structured prediction, such as image classification and regression tasks. However, while task-specific forms of confidence score estimation have been investigated by the speech and machine translation communities, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider uncertainty estimation for sequence data at the token-level and complete sequence-level, provide interpretations for, and applications of, various measures of uncertainty and discuss the challenges associated with obtaining them. This work also explores the practical challenges associated with obtaining uncertainty estimates for structured predictions tasks and provides baselines for token-level error detection, sequence-level prediction rejection, and sequence-level out-of-domain input detection using ensembles of auto-regressive transformer models trained on the WMT'14 English-French and WMT'17 English-German translation and LibriSpeech speech recognition datasets.

  Access Paper or Ask Questions