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

Unsupervised vs. transfer learning for multimodal one-shot matching of speech and images

Aug 14, 2020
Leanne Nortje, Herman Kamper

We consider the task of multimodal one-shot speech-image matching. An agent is shown a picture along with a spoken word describing the object in the picture, e.g. cookie, broccoli and ice-cream. After observing one paired speech-image example per class, it is shown a new set of unseen pictures, and asked to pick the "ice-cream". Previous work attempted to tackle this problem using transfer learning: supervised models are trained on labelled background data not containing any of the one-shot classes. Here we compare transfer learning to unsupervised models trained on unlabelled in-domain data. On a dataset of paired isolated spoken and visual digits, we specifically compare unsupervised autoencoder-like models to supervised classifier and Siamese neural networks. In both unimodal and multimodal few-shot matching experiments, we find that transfer learning outperforms unsupervised training. We also present experiments towards combining the two methodologies, but find that transfer learning still performs best (despite idealised experiments showing the benefits of unsupervised learning).

* Accepted at Interspeech 2020 

  Access Paper or Ask Questions

Improving noise robustness of automatic speech recognition via parallel data and teacher-student learning

Jan 11, 2019
Ladislav Mošner, Minhua Wu, Anirudh Raju, Sree Hari Krishnan Parthasarathi, Kenichi Kumatani, Shiva Sundaram, Roland Maas, Björn Hoffmeister

For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits selection method which only preserves the k highest values to prevent wrong emphasis of knowledge from the teacher and to reduce bandwidth needed for transferring data. We incorporate up to 8000 hours of untranscribed data for training and present our results on sequence trained models apart from cross entropy trained ones. The best sequence trained student model yields relative word error rate (WER) reductions of approximately 10.1%, 28.7% and 19.6% on our clean, simulated noisy and real test sets respectively comparing to a sequence trained teacher.

  Access Paper or Ask Questions

Robust Over-the-Air Adversarial Examples Against Automatic Speech Recognition Systems

Aug 05, 2019
Lea Schönherr, Steffen Zeiler, Thorsten Holz, Dorothea Kolossa

Automatic speech recognition (ASR) systems are possible to fool via targeted adversarial examples. These can induce the ASR to produce arbitrary transcriptions in response to any type of audio signal, be it speech, environmental sounds, or music. However, in general, those adversarial examples did not work in a real-world setup, where the examples are played over the air but have to be fed into the ASR system directly. In some cases, where the adversarial examples could be successfully played over the air, the attacks require precise information about the room where the attack takes place in order to tailor the adversarial examples to a specific setup and are not transferable to other rooms. Other attacks, which are robust in an over-the-air attack, are either handcrafted examples or human listeners can easily recognize the target transcription, once they have been alerted to its content. In this paper, we demonstrate the first generic algorithm that produces adversarial examples which remain robust in an over-the-air attack such that the ASR system transcribes the target transcription after actually being replayed. For the proposed algorithm, guessing a rough approximation of the room characteristics is enough and no actual access to the room is required. We use the ASR system Kaldi to demonstrate the attack and employ a room-impulse-response simulator to harden the adversarial examples against varying room characteristics. Further, the algorithm can also utilize psychoacoustics to hide changes of the original audio signal below the human thresholds of hearing. We show that the adversarial examples work for varying room setups, but also can be tailored to specific room setups. As a result, an attacker can optimize adversarial examples for any target transcription and to arbitrary rooms. Additionally, the adversarial examples remain transferable to varying rooms with a high probability.

  Access Paper or Ask Questions

Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition

Jul 10, 2018
Chun-Fu Chen, Quanfu Fan, Neil Mallinar, Tom Sercu, Rogerio Feris

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has different computational complexity at different branches. Through frequent merging of features from branches at distinct scales, our model obtains multi-scale features while using less computation. The proposed approach demonstrates improvement of model efficiency and performance on both object recognition and speech recognition tasks,using popular architectures including ResNet and ResNeXt. For object recognition, our approach reduces computation by 33% on object recognition while improving accuracy with 0.9%. Furthermore, our model surpasses state-of-the-art CNN acceleration approaches by a large margin in accuracy and FLOPs reduction. On the task of speech recognition, our proposed multi-scale CNNs save 30% FLOPs with slightly better word error rates, showing good generalization across domains.

  Access Paper or Ask Questions

Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks

Jan 23, 2018
Yonatan Belinkov, Lluís Màrquez, Hassan Sajjad, Nadir Durrani, Fahim Dalvi, James Glass

While neural machine translation (NMT) models provide improved translation quality in an elegant, end-to-end framework, it is less clear what they learn about language. Recent work has started evaluating the quality of vector representations learned by NMT models on morphological and syntactic tasks. In this paper, we investigate the representations learned at different layers of NMT encoders. We train NMT systems on parallel data and use the trained models to extract features for training a classifier on two tasks: part-of-speech and semantic tagging. We then measure the performance of the classifier as a proxy to the quality of the original NMT model for the given task. Our quantitative analysis yields interesting insights regarding representation learning in NMT models. For instance, we find that higher layers are better at learning semantics while lower layers tend to be better for part-of-speech tagging. We also observe little effect of the target language on source-side representations, especially with higher quality NMT models.

* IJCNLP 8 (2017), volume 1, 1-10 
* IJCNLP 2017 

  Access Paper or Ask Questions

Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition

Jun 30, 2020
Maarten Van Segbroeck, Harish Mallidih, Brian King, I-Fan Chen, Gurpreet Chadha, Roland Maas

Acoustic models in real-time speech recognition systems typically stack multiple unidirectional LSTM layers to process the acoustic frames over time. Performance improvements over vanilla LSTM architectures have been reported by prepending a stack of frequency-LSTM (FLSTM) layers to the time LSTM. These FLSTM layers can learn a more robust input feature to the time LSTM layers by modeling time-frequency correlations in the acoustic input signals. A drawback of FLSTM based architectures however is that they operate at a predefined, and tuned, window size and stride, referred to as 'view' in this paper. We present a simple and efficient modification by combining the outputs of multiple FLSTM stacks with different views, into a dimensionality reduced feature representation. The proposed multi-view FLSTM architecture allows to model a wider range of time-frequency correlations compared to an FLSTM model with single view. When trained on 50K hours of English far-field speech data with CTC loss followed by sMBR sequence training, we show that the multi-view FLSTM acoustic model provides relative Word Error Rate (WER) improvements of 3-7% for different speaker and acoustic environment scenarios over an optimized single FLSTM model, while retaining a similar computational footprint.

  Access Paper or Ask Questions

Fine-grained robust prosody transfer for single-speaker neural text-to-speech

Jul 04, 2019
Viacheslav Klimkov, Srikanth Ronanki, Jonas Rohnke, Thomas Drugman

We present a neural text-to-speech system for fine-grained prosody transfer from one speaker to another. Conventional approaches for end-to-end prosody transfer typically use either fixed-dimensional or variable-length prosody embedding via a secondary attention to encode the reference signal. However, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough to speaker variability, especially in the case of a reference signal coming from an unseen speaker. Therefore, we propose decoupling of the reference signal alignment from the overall system. For this purpose, we pre-compute phoneme-level time stamps and use them to aggregate prosodic features per phoneme, injecting them into a sequence-to-sequence text-to-speech system. We incorporate a variational auto-encoder to further enhance the latent representation of prosody embeddings. We show that our proposed approach is significantly more stable and achieves reliable prosody transplantation from an unseen speaker. We also propose a solution to the use case in which the transcription of the reference signal is absent. We evaluate all our proposed methods using both objective and subjective listening tests.

* 5 pages, 7 figures, Accepted for Interspeech 2019 

  Access Paper or Ask Questions

Waveform generation for text-to-speech synthesis using pitch-synchronous multi-scale generative adversarial networks

Oct 30, 2018
Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku

The state-of-the-art in text-to-speech synthesis has recently improved considerably due to novel neural waveform generation methods, such as WaveNet. However, these methods suffer from their slow sequential inference process, while their parallel versions are difficult to train and even more expensive computationally. Meanwhile, generative adversarial networks (GANs) have achieved impressive results in image generation and are making their way into audio applications; parallel inference is among their lucrative properties. By adopting recent advances in GAN training techniques, this investigation studies waveform generation for TTS in two domains (speech signal and glottal excitation). Listening test results show that while direct waveform generation with GAN is still far behind WaveNet, a GAN-based glottal excitation model can achieve quality and voice similarity on par with a WaveNet vocoder.

* Submitted to ICASSP 2019 

  Access Paper or Ask Questions

Cross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed Speech

Sep 22, 2021
Ida Szubert, Omri Abend, Nathan Schneider, Samuel Gibbon, Sharon Goldwater, Mark Steedman

While corpora of child speech and child-directed speech (CDS) have enabled major contributions to the study of child language acquisition, semantic annotation for such corpora is still scarce and lacks a uniform standard. We compile two CDS corpora with sentential logical forms, one in English and the other in Hebrew. In compiling the corpora we employ a methodology that enforces a cross-linguistically consistent representation, building on recent advances in dependency representation and semantic parsing. The corpora are based on a sizable portion of Brown's Adam corpus from CHILDES (about 80% of its child-directed utterances), and to all child-directed utterances from Berman's Hebrew CHILDES corpus Hagar. We begin by annotating the corpora with the Universal Dependencies (UD) scheme for syntactic annotation, motivated by its applicability to a wide variety of domains and languages. We then proceed by applying an automatic method for transducing sentential logical forms (LFs) from UD structures. The two representations have complementary strengths: UD structures are language-neutral and support direct annotation, whereas LFs are neutral as to the interface between syntax and semantics, and transparently encode semantic distinctions. We verify the quality of the annotated UD annotation using an inter-annotator agreement study. We then demonstrate the utility of the compiled corpora through a longitudinal corpus study of the prevalence of different syntactic and semantic phenomena.

  Access Paper or Ask Questions

Semi-Supervised Speech Recognition via Graph-based Temporal Classification

Oct 29, 2020
Niko Moritz, Takaaki Hori, Jonathan Le Roux

Semi-supervised learning has demonstrated promising results in automatic speech recognition (ASR) by self-training using a seed ASR model with pseudo-labels generated for unlabeled data. The effectiveness of this approach largely relies on the pseudo-label accuracy, for which typically only the 1-best ASR hypothesis is used. However, alternative ASR hypotheses of an N-best list can provide more accurate labels for an unlabeled speech utterance and also reflect uncertainties of the seed ASR model. In this paper, we propose a generalized form of the connectionist temporal classification (CTC) objective that accepts a graph representation of the training targets. The newly proposed graph-based temporal classification (GTC) objective is applied for self-training with WFST-based supervision, which is generated from an N-best list of pseudo-labels. In this setup, GTC is used to learn not only a temporal alignment, similarly to CTC, but also a label alignment to obtain the optimal pseudo-label sequence from the weighted graph. Results show that this approach can effectively exploit an N-best list of pseudo-labels with associated scores, outperforming standard pseudo-labeling by a large margin, with ASR results close to an oracle experiment in which the best hypotheses of the N-best lists are selected manually.

* Submitted to ICASSP 2021 

  Access Paper or Ask Questions