Audio augmentation for speech recognition

Ko, Tom; Peddinti, Vijayaditya; Povey, Daniel; Khudanpur, Sanjeev

doi:10.21437/interspeech.2015-711

Cited by 813 publications

(410 citation statements)

References 11 publications

Supporting

Mentioning

379

Contrasting

Order By: Relevance

“…We extracted 80-channel log-mel filterbank coefficients computed with a 25-ms window that was shifted every 10ms with Kaldi [19]. We applied three-fold speed perturbation [20] and SpecAugment [21]. The vocabularies were constructed by the byte pair encoding (BPE) algorithm [22] with 10k and 1k units for AED and RNN-T models, respectively.…”

Section: Experimental Evaluations 41 Experimental Setupmentioning

confidence: 99%

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR

Inaguma

Kawahara

2021

Interspeech 2021

View full text Add to dashboard Cite

While attention-based encoder-decoder (AED) models have been successfully extended to the online variants for streaming automatic speech recognition (ASR), such as monotonic chunkwise attention (MoChA), the models still have a large label emission latency because of the unconstrained end-to-end training objective. Previous works tackled this problem by leveraging alignment information to control the timing to emit tokens during training. In this work, we propose a simple alignmentfree regularization method, StableEmit, to encourage MoChA to emit tokens earlier. StableEmit discounts the selection probabilities in hard monotonic attention for token boundary detection by a constant factor and regularizes them to recover the total attention mass during training. As a result, the scale of the selection probabilities is increased, and the values can reach a threshold for token emission earlier, leading to a reduction of emission latency and deletion errors. Moreover, StableEmit can be combined with methods that constraint alignments to further improve the accuracy and latency. Experimental evaluations with LSTM and Conformer encoders demonstrate that StableEmit significantly reduces the recognition errors and the emission latency simultaneously. We also show that the use of alignment information is complementary in both metrics.

show abstract

Section: Experimental Evaluations 41 Experimental Setupmentioning

confidence: 99%

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR

Inaguma

Kawahara

2021

Interspeech 2021

View full text Add to dashboard Cite

show abstract

“…As an upperbound experiment, we compare with a supervised-only setting where we have 650 hours for UK English and 3700 hours for Italian. The supervised data is augmented 3x with speed perturbation [24]. For evaluation, we use a 14 hour test set for UK English and a 20 hour test set for Italian.…”

Section: Datamentioning

confidence: 99%

Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition

Manohar¹,

Likhomanenko²,

Xu³

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, we introduce the Kaizen framework that uses a continuously improving teacher to generate pseudo-labels for semi-supervised training. The proposed approach uses a teacher model which is updated as the exponential moving average of the student model parameters. This can be seen as a continuous version of the iterative pseudo-labeling approach for semi-supervised training. It is applicable for different training criteria, and in this paper we demonstrate it for frame-level hybrid hidden Markov model -deep neural network (HMM-DNN) models and sequence-level connectionist temporal classification (CTC) based models. The proposed approach shows more than 10% word error rate (WER) reduction over standard teacher-student training and more than 50% relative WER reduction over 10 hour supervised baseline when using large scale realistic unsupervised public videos in UK English and Italian languages.

show abstract

“…We used Must-C (Di Gangi et al, 2019), Must-C v2 2 , ST-TED (Jan et al, 2018), Librispeech (Panayotov et al, 2015), and TEDLIUM2 (Rousseau et al, 2012) corpora. We used the cleaned version of ST-TED following data was augmented by three-fold speed perturbation (Ko et al, 2015) with speed ratios of 0.9, 1.0, and 1.1 except for Librispeech. We removed case information and punctuation marks except for apostrophes from the transcripts.…”

Section: Asrmentioning

confidence: 99%

ESPnet-ST IWSLT 2021 Offline Speech Translation System

Inaguma¹,

Yan²,

Dalmia³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowledge distillation (SeqKD) for end-to-end (E2E) speech translation. Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext. On the architecture side, we adopted the Conformer encoder and the Multi-Decoder architecture, which equips dedicated decoders for speech recognition and translation tasks in a unified encoder-decoder model and enables search in both source and target language spaces during inference. We also significantly improved audio segmentation by using the pyannote.audio toolkit and merging multiple short segments for long context modeling. Experimental evaluations showed that each of them contributed to large improvements in translation performance. Our best E2E system combined all the above techniques with model ensembling and achieved 31.4 BLEU on the 2-ref of tst2021 and 21.2 BLEU and 19.3 BLEU on the two single references of tst2021. * *Equal contribution 1 https://sites.google.com/ view/iwslt-evaluation-2019/ speech-translation/off-limit-ted-talks 2 https://ict.fbk.eu/ must-c-release-v2-0/

show abstract

Audio augmentation for speech recognition

Cited by 813 publications

References 11 publications

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR

StableEmit: Selection Probability Discount for Reducing Emission Latency of Streaming Monotonic Attention ASR

Kaizen: Continuously improving teacher using Exponential Moving Average for semi-supervised speech recognition

ESPnet-ST IWSLT 2021 Offline Speech Translation System

Contact Info

Product

Resources

About