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

X-Vectors with Multi-Scale Aggregation for Speaker Diarization

May 16, 2021
Myungjong Kim, Vijendra Raj Apsingekar, Divya Neelagiri

Speaker diarization is the process of labeling different speakers in a speech signal. Deep speaker embeddings are generally extracted from short speech segments and clustered to determine the segments belong to same speaker identity. The x-vector, which embeds segment-level speaker characteristics by statistically pooling frame-level representations, is one of the most widely used deep speaker embeddings in speaker diarization. Multi-scale aggregation, which employs multi-scale representations from different layers, has recently successfully been used in short duration speaker verification. In this paper, we investigate a multi-scale aggregation approach in an x-vector embedding framework for speaker diarization by exploiting multiple statistics pooling layers from different frame-level layers. Thus, it is expected that x-vectors with multi-scale aggregation have the potential to capture meaningful speaker characteristics from short segments, effectively taking advantage of different information at multiple layers. Experimental evaluation on the CALLHOME dataset showed that our approach provides substantial improvement over the baseline x-vectors.

  Access Paper or Ask Questions

Tune-In: Training Under Negative Environments with Interference for Attention Networks Simulating Cocktail Party Effect

Mar 02, 2021
Jun Wang, Max W. Y. Lam, Dan Su, Dong Yu

We study the cocktail party problem and propose a novel attention network called Tune-In, abbreviated for training under negative environments with interference. It firstly learns two separate spaces of speaker-knowledge and speech-stimuli based on a shared feature space, where a new block structure is designed as the building block for all spaces, and then cooperatively solves different tasks. Between the two spaces, information is cast towards each other via a novel cross- and dual-attention mechanism, mimicking the bottom-up and top-down processes of a human's cocktail party effect. It turns out that substantially discriminative and generalizable speaker representations can be learnt in severely interfered conditions via our self-supervised training. The experimental results verify this seeming paradox. The learnt speaker embedding has superior discriminative power than a standard speaker verification method; meanwhile, Tune-In achieves remarkably better speech separation performances in terms of SI-SNRi and SDRi consistently in all test modes, and especially at lower memory and computational consumption, than state-of-the-art benchmark systems.

* Accepted in AAAI 2021 

  Access Paper or Ask Questions

Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understanding

Feb 12, 2021
Milind Rao, Pranav Dheram, Gautam Tiwari, Anirudh Raju, Jasha Droppo, Ariya Rastrow, Andreas Stolcke

Spoken language understanding (SLU) systems extract transcriptions, as well as semantics of intent or named entities from speech, and are essential components of voice activated systems. SLU models, which either directly extract semantics from audio or are composed of pipelined automatic speech recognition (ASR) and natural language understanding (NLU) models, are typically trained via differentiable cross-entropy losses, even when the relevant performance metrics of interest are word or semantic error rates. In this work, we propose non-differentiable sequence losses based on SLU metrics as a proxy for semantic error and use the REINFORCE trick to train ASR and SLU models with this loss. We show that custom sequence loss training is the state-of-the-art on open SLU datasets and leads to 6% relative improvement in both ASR and NLU performance metrics on large proprietary datasets. We also demonstrate how the semantic sequence loss training paradigm can be used to update ASR and SLU models without transcripts, using semantic feedback alone.

* Proc. IEEE ICASSP 2021 

  Access Paper or Ask Questions

Convo: What does conversational programming need? An exploration of machine learning interface design

Mar 03, 2020
Jessica Van Brummelen, Kevin Weng, Phoebe Lin, Catherine Yeo

Vast improvements in natural language understanding and speech recognition have paved the way for conversational interaction with computers. While conversational agents have often been used for short goal-oriented dialog, we know little about agents for developing computer programs. To explore the utility of natural language for programming, we conducted a study ($n$=45) comparing different input methods to a conversational programming system we developed. Participants completed novice and advanced tasks using voice-based, text-based, and voice-or-text-based systems. We found that users appreciated aspects of each system (e.g., voice-input efficiency, text-input precision) and that novice users were more optimistic about programming using voice-input than advanced users. Our results show that future conversational programming tools should be tailored to users' programming experience and allow users to choose their preferred input mode. To reduce cognitive load, future interfaces can incorporate visualizations and possess custom natural language understanding and speech recognition models for programming.

* 9 pages, 7 figures, submitted to VL/HCC 2020, for associated user study video: 

  Access Paper or Ask Questions

Audio-Visual Target Speaker Extraction on Multi-Talker Environment using Event-Driven Cameras

Dec 05, 2019
Ander Arriandiaga, Giovanni Morrone, Luca Pasa, Leonardo Badino, Chiara Bartolozzi

In this work, we propose a new method to address audio-visual target speaker extraction in multi-talker environments using event-driven cameras. All audio-visual speech separation approaches use a frame-based video to extract visual features. However, these frame-based cameras usually work at 30 frames per second. This limitation makes it difficult to process an audio-visual signal with low latency. In order to overcome this limitation, we propose using event-driven cameras due to their high temporal resolution and low latency. Recent work showed that the use of landmark motion features is very important in order to get good results on audio-visual speech separation. Thus, we use event-driven vision sensors from which the extraction of motion is available at lower latency computational cost. A stacked Bidirectional LSTM is trained to predict an Ideal Amplitude Mask before post-processing to get a clean audio signal. The performance of our model is close to those yielded in frame-based fashion.

  Access Paper or Ask Questions

Transformer ASR with Contextual Block Processing

Oct 16, 2019
Emiru Tsunoo, Yosuke Kashiwagi, Toshiyuki Kumakura, Shinji Watanabe

The Transformer self-attention network has recently shown promising performance as an alternative to recurrent neural networks (RNNs) in end-to-end (E2E) automatic speech recognition (ASR) systems. However, the Transformer has a drawback in that the entire input sequence is required to compute self-attention. In this paper, we propose a new block processing method for the Transformer encoder by introducing a context-aware inheritance mechanism. An additional context embedding vector handed over from the previously processed block helps to encode not only local acoustic information but also global linguistic, channel, and speaker attributes. We introduce a novel mask technique to implement the context inheritance to train the model efficiently. Evaluations of the Wall Street Journal (WSJ), Librispeech, VoxForge Italian, and AISHELL-1 Mandarin speech recognition datasets show that our proposed contextual block processing method outperforms naive block processing consistently. Furthermore, the attention weight tendency of each layer is analyzed to clarify how the added contextual inheritance mechanism models the global information.

* Accepted for ASRU 2019 

  Access Paper or Ask Questions

Maximizing Mutual Information for Tacotron

Aug 30, 2019
Peng Liu, Xixin Wu, Shiyin Kang, Guangzhi Li, Dan Su, Dong Yu

End-to-end speech synthesis method such as Tacotron, Tacotron2 and Transformer-TTS already achieves close to human quality performance. However compared to HMM-based method or NN-based frame-to-frame regression method, it is prone to some bad cases, such as missing words, repeating words and incomplete synthesis. More seriously, we cannot know whether such errors exist in a synthesized waveform or not unless we listen to it. We attribute the comparatively high sentence error rate to the local information preference of conditional autoregressive models. Inspired by the success of InfoGAN in learning interpretable representation by a mutual information regularization, in this paper, we propose to maximize the mutual information between the predicted acoustic features and the input text for end-to-end speech synthesis methods to address the local information preference problem and avoid such bad cases. What is more, we provide an indicator to detect errors in the predicted acoustic features as a byproduct. Experiment results show that our method can reduce the rate of bad cases and provide a reliable indicator to detect bad cases automatically.

  Access Paper or Ask Questions

A CNN-based tool for automatic tongue contour tracking in ultrasound images

Jul 24, 2019
Jian Zhu, Will Styler, Ian Calloway

For speech research, ultrasound tongue imaging provides a non-invasive means for visualizing tongue position and movement during articulation. Extracting tongue contours from ultrasound images is a basic step in analyzing ultrasound data but this task often requires non-trivial manual annotation. This study presents an open source tool for fully automatic tracking of tongue contours in ultrasound frames using neural network based methods. We have implemented and systematically compared two convolutional neural networks, U-Net and DenseU-Net, under different conditions. Though both models can perform automatic contour tracking with comparable accuracy, Dense U-Net architecture seems more generalizable across test datasets while U-Net has faster extraction speed. Our comparison also shows that the choice of loss function and data augmentation have a greater effect on tracking performance in this task. This public available segmentation tool shows considerable promise for the automated tongue contour annotation of ultrasound images in speech research.

  Access Paper or Ask Questions

Hierarchical Sequence to Sequence Voice Conversion with Limited Data

Jul 15, 2019
Praveen Narayanan, Punarjay Chakravarty, Francois Charette, Gint Puskorius

We present a voice conversion solution using recurrent sequence to sequence modeling for DNNs. Our solution takes advantage of recent advances in attention based modeling in the fields of Neural Machine Translation (NMT), Text-to-Speech (TTS) and Automatic Speech Recognition (ASR). The problem consists of converting between voices in a parallel setting when {\it $<$source,target$>$} audio pairs are available. Our seq2seq architecture makes use of a hierarchical encoder to summarize input audio frames. On the decoder side, we use an attention based architecture used in recent TTS works. Since there is a dearth of large multispeaker voice conversion databases needed for training DNNs, we resort to training the network with a large single speaker dataset as an autoencoder. This is then adapted for the smaller multispeaker voice conversion datasets available for voice conversion. In contrast with other voice conversion works that use $F_0$, duration and linguistic features, our system uses mel spectrograms as the audio representation. Output mel frames are converted back to audio using a wavenet vocoder.

  Access Paper or Ask Questions

Self-Attentional Models for Lattice Inputs

Jun 04, 2019
Matthias Sperber, Graham Neubig, Ngoc-Quan Pham, Alex Waibel

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic analyses. Previous work has extended recurrent neural networks to model lattice inputs and achieved improvements in various tasks, but these models suffer from very slow computation speeds. This paper extends the recently proposed paradigm of self-attention to handle lattice inputs. Self-attention is a sequence modeling technique that relates inputs to one another by computing pairwise similarities and has gained popularity for both its strong results and its computational efficiency. To extend such models to handle lattices, we introduce probabilistic reachability masks that incorporate lattice structure into the model and support lattice scores if available. We also propose a method for adapting positional embeddings to lattice structures. We apply the proposed model to a speech translation task and find that it outperforms all examined baselines while being much faster to compute than previous neural lattice models during both training and inference.

* ACL 2019 

  Access Paper or Ask Questions