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

Leveraging neural representations for facilitating access to untranscribed speech from endangered languages

Mar 26, 2021
Nay San, Martijn Bartelds, Mitchell Browne, Lily Clifford, Fiona Gibson, John Mansfield, David Nash, Jane Simpson, Myfany Turpin, Maria Vollmer, Sasha Wilmoth, Dan Jurafsky

For languages with insufficient resources to train speech recognition systems, query-by-example spoken term detection (QbE-STD) offers a way of accessing an untranscribed speech corpus by helping identify regions where spoken query terms occur. Yet retrieval performance can be poor when the query and corpus are spoken by different speakers and produced in different recording conditions. Using data selected from a variety of speakers and recording conditions from 7 Australian Aboriginal languages and a regional variety of Dutch, all of which are endangered or vulnerable, we evaluated whether QbE-STD performance on these languages could be improved by leveraging representations extracted from the pre-trained English wav2vec 2.0 model. Compared to the use of Mel-frequency cepstral coefficients and bottleneck features, we find that representations from the middle layers of the wav2vec 2.0 Transformer offer large gains in task performance (between 56% and 86%). While features extracted using the pre-trained English model yielded improved detection on all the evaluation languages, better detection performance was associated with the evaluation language's phonological similarity to English.

* Submitted to Interspeech 2021 

  Access Paper or Ask Questions

Learning Representations of Emotional Speech with Deep Convolutional Generative Adversarial Networks

Apr 22, 2017
Jonathan Chang, Stefan Scherer

Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states are often "overshadowed" by voice characteristics relating to emotional intensity or emotional activation. In this work we explore a representation learning approach that automatically derives discriminative representations of emotional speech. In particular, we investigate two machine learning strategies to improve classifier performance: (1) utilization of unlabeled data using a deep convolutional generative adversarial network (DCGAN), and (2) multitask learning. Within our extensive experiments we leverage a multitask annotated emotional corpus as well as a large unlabeled meeting corpus (around 100 hours). Our speaker-independent classification experiments show that in particular the use of unlabeled data in our investigations improves performance of the classifiers and both fully supervised baseline approaches are outperformed considerably. We improve the classification of emotional valence on a discrete 5-point scale to 43.88% and on a 3-point scale to 49.80%, which is competitive to state-of-the-art performance.

  Access Paper or Ask Questions

WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition

Sep 21, 2017
Ahmed Ali, Preslav Nakov, Peter Bell, Steve Renals

We study the problem of evaluating automatic speech recognition (ASR) systems that target dialectal speech input. A major challenge in this case is that the orthography of dialects is typically not standardized. From an ASR evaluation perspective, this means that there is no clear gold standard for the expected output, and several possible outputs could be considered correct according to different human annotators, which makes standard word error rate (WER) inadequate as an evaluation metric. Such a situation is typical for machine translation (MT), and thus we borrow ideas from an MT evaluation metric, namely TERp, an extension of translation error rate which is closely-related to WER. In particular, in the process of comparing a hypothesis to a reference, we make use of spelling variants for words and phrases, which we mine from Twitter in an unsupervised fashion. Our experiments with evaluating ASR output for Egyptian Arabic, and further manual analysis, show that the resulting WERd (i.e., WER for dialects) metric, a variant of TERp, is more adequate than WER for evaluating dialectal ASR.

* ASRU-2017 

  Access Paper or Ask Questions

A New Amharic Speech Emotion Dataset and Classification Benchmark

Jan 07, 2022
Ephrem A. Retta, Eiad Almekhlafi, Richard Sutcliffe, Mustafa Mhamed, Haider Ali, Jun Feng

In this paper we present the Amharic Speech Emotion Dataset (ASED), which covers four dialects (Gojjam, Wollo, Shewa and Gonder) and five different emotions (neutral, fearful, happy, sad and angry). We believe it is the first Speech Emotion Recognition (SER) dataset for the Amharic language. 65 volunteer participants, all native speakers, recorded 2,474 sound samples, two to four seconds in length. Eight judges assigned emotions to the samples with high agreement level (Fleiss kappa = 0.8). The resulting dataset is freely available for download. Next, we developed a four-layer variant of the well-known VGG model which we call VGGb. Three experiments were then carried out using VGGb for SER, using ASED. First, we investigated whether Mel-spectrogram features or Mel-frequency Cepstral coefficient (MFCC) features work best for Amharic. This was done by training two VGGb SER models on ASED, one using Mel-spectrograms and the other using MFCC. Four forms of training were tried, standard cross-validation, and three variants based on sentences, dialects and speaker groups. Thus, a sentence used for training would not be used for testing, and the same for a dialect and speaker group. The conclusion was that MFCC features are superior under all four training schemes. MFCC was therefore adopted for Experiment 2, where VGGb and three other existing models were compared on ASED: RESNet50, Alex-Net and LSTM. VGGb was found to have very good accuracy (90.73%) as well as the fastest training time. In Experiment 3, the performance of VGGb was compared when trained on two existing SER datasets, RAVDESS (English) and EMO-DB (German) as well as on ASED (Amharic). Results are comparable across these languages, with ASED being the highest. This suggests that VGGb can be successfully applied to other languages. We hope that ASED will encourage researchers to experiment with other models for Amharic SER.

* 16 pages, 12 tables, 6 figures 

  Access Paper or Ask Questions

Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM

Jun 08, 2017
Takaaki Hori, Shinji Watanabe, Yu Zhang, William Chan

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is a deep Convolutional Neural Network (CNN) based on the VGG network. The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder. During the beam search process, we combine the CTC predictions, the attention-based decoder predictions and a separately trained LSTM language model. We achieve a 5-10\% error reduction compared to prior systems on spontaneous Japanese and Chinese speech, and our end-to-end model beats out traditional hybrid ASR systems.

* Accepted for INTERSPEECH 2017 

  Access Paper or Ask Questions

Training a Neural Speech Waveform Model using Spectral Losses of Short-Time Fourier Transform and Continuous Wavelet Transform

Apr 07, 2019
Shinji Takaki, Hirokazu Kameoka, Junichi Yamagishi

Recently, we proposed short-time Fourier transform (STFT)-based loss functions for training a neural speech waveform model. In this paper, we generalize the above framework and propose a training scheme for such models based on spectral amplitude and phase losses obtained by either STFT or continuous wavelet transform (CWT), or both of them. Since CWT is capable of having time and frequency resolutions different from those of STFT and is cable of considering those closer to human auditory scales, the proposed loss functions could provide complementary information on speech signals. Experimental results showed that it is possible to train a high-quality model by using the proposed CWT spectral loss and is as good as one using STFT-based loss.

* Submitted to Interspeech 2019, Graz, Austria 

  Access Paper or Ask Questions

Direct Acoustics-to-Word Models for English Conversational Speech Recognition

Mar 22, 2017
Kartik Audhkhasi, Bhuvana Ramabhadran, George Saon, Michael Picheny, David Nahamoo

Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they are not truly end-to-end in the sense of mapping acoustics directly to words without an intermediate phone representation. In this paper, we present the first results employing direct acoustics-to-word CTC models on two well-known public benchmark tasks: Switchboard and CallHome. These models do not require an LM or even a decoder at run-time and hence recognize speech with minimal complexity. However, due to the large number of word output units, CTC word models require orders of magnitude more data to train reliably compared to traditional systems. We present some techniques to mitigate this issue. Our CTC word model achieves a word error rate of 13.0%/18.8% on the Hub5-2000 Switchboard/CallHome test sets without any LM or decoder compared with 9.6%/16.0% for phone-based CTC with a 4-gram LM. We also present rescoring results on CTC word model lattices to quantify the performance benefits of a LM, and contrast the performance of word and phone CTC models.

* Submitted to Interspeech-2017 

  Access Paper or Ask Questions

Exploring Wav2vec 2.0 fine-tuning for improved speech emotion recognition

Oct 28, 2021
Li-Wei Chen, Alexander Rudnicky

While wav2vec 2.0 has been proposed for speech recognition (ASR), it can also be used for speech emotion recognition (SER); its performance can be significantly improved using different fine-tuning strategies. Two baseline methods, vanilla fine-tuning (V-FT) and task adaptive pretraining (TAPT) are first presented. We show that V-FT is able to outperform state-of-the-art models on the IEMOCAP dataset. TAPT, an existing NLP fine-tuning strategy, further improves the performance on SER. We also introduce a novel fine-tuning method termed P-TAPT, which modifies the TAPT objective to learn contextualized emotion representations. Experiments show that P-TAPT performs better than TAPT especially under low-resource settings. Compared to prior works in this literature, our top-line system achieved a 7.4% absolute improvement on unweighted accuracy (UA) over the state-of-the-art performance on IEMOCAP. Our code is publicly available.

* Submitted to ICASSP 2022 

  Access Paper or Ask Questions

SCaLa: Supervised Contrastive Learning for End-to-End Automatic Speech Recognition

Oct 08, 2021
Li Fu, Xiaoxiao Li, Runyu Wang, Zhengchen Zhang, Youzheng Wu, Xiaodong He, Bowen Zhou

End-to-end Automatic Speech Recognition (ASR) models are usually trained to reduce the losses of the whole token sequences, while neglecting explicit phonemic-granularity supervision. This could lead to recognition errors due to similar-phoneme confusion or phoneme reduction. To alleviate this problem, this paper proposes a novel framework of Supervised Contrastive Learning (SCaLa) to enhance phonemic information learning for end-to-end ASR systems. Specifically, we introduce the self-supervised Masked Contrastive Predictive Coding (MCPC) into the fully-supervised setting. To supervise phoneme learning explicitly, SCaLa first masks the variable-length encoder features corresponding to phonemes given phoneme forced-alignment extracted from a pre-trained acoustic model, and then predicts the masked phonemes via contrastive learning. The phoneme forced-alignment can mitigate the noise of positive-negative pairs in self-supervised MCPC. Experimental results conducted on reading and spontaneous speech datasets show that the proposed approach achieves 2.84% and 1.38% Character Error Rate (CER) reductions compared to the baseline, respectively.

* Submitted to ICASSP 2022 

  Access Paper or Ask Questions