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

Multi-modal Automated Speech Scoring using Attention Fusion

May 17, 2020
Manraj Singh Grover, Yaman Kumar, Sumit Sarin, Payman Vafaee, Mika Hama, Rajiv Ratn Shah

In this study, we propose a novel multi-modal end-to-end neural approach for automated assessment of non-native English speakers' spontaneous speech using attention fusion. The pipeline employs Bi-directional Recurrent Convolutional Neural Networks and Bi-directional Long Short-Term Memory Neural Networks to encode acoustic and lexical cues from spectrograms and transcriptions, respectively. Attention fusion is performed on these learned predictive features to learn complex interactions between different modalities before final scoring. We compare our model with strong baselines and find combined attention to both lexical and acoustic cues significantly improves the overall performance of the system. Further, we present a qualitative and quantitative analysis of our model.

* Submitted to INTERSPEECH 2020 

  Access Paper or Ask Questions

Conformal prediction for text infilling and part-of-speech prediction

Nov 04, 2021
Neil Dey, Jing Ding, Jack Ferrell, Carolina Kapper, Maxwell Lovig, Emiliano Planchon, Jonathan P Williams

Modern machine learning algorithms are capable of providing remarkably accurate point-predictions; however, questions remain about their statistical reliability. Unlike conventional machine learning methods, conformal prediction algorithms return confidence sets (i.e., set-valued predictions) that correspond to a given significance level. Moreover, these confidence sets are valid in the sense that they guarantee finite sample control over type 1 error probabilities, allowing the practitioner to choose an acceptable error rate. In our paper, we propose inductive conformal prediction (ICP) algorithms for the tasks of text infilling and part-of-speech (POS) prediction for natural language data. We construct new conformal prediction-enhanced bidirectional encoder representations from transformers (BERT) and bidirectional long short-term memory (BiLSTM) algorithms for POS tagging and a new conformal prediction-enhanced BERT algorithm for text infilling. We analyze the performance of the algorithms in simulations using the Brown Corpus, which contains over 57,000 sentences. Our results demonstrate that the ICP algorithms are able to produce valid set-valued predictions that are small enough to be applicable in real-world applications. We also provide a real data example for how our proposed set-valued predictions can improve machine generated audio transcriptions.

  Access Paper or Ask Questions

Hallucination of speech recognition errors with sequence to sequence learning

Mar 31, 2021
Prashant Serai, Vishal Sunder, Eric Fosler-Lussier

Automatic Speech Recognition (ASR) is an imperfect process that results in certain mismatches in ASR output text when compared to plain written text or transcriptions. When plain text data is to be used to train systems for spoken language understanding or ASR, a proven strategy to reduce said mismatch and prevent degradations, is to hallucinate what the ASR outputs would be given a gold transcription. Prior work in this domain has focused on modeling errors at the phonetic level, while using a lexicon to convert the phones to words, usually accompanied by an FST Language model. We present novel end-to-end models to directly predict hallucinated ASR word sequence outputs, conditioning on an input word sequence as well as a corresponding phoneme sequence. This improves prior published results for recall of errors from an in-domain ASR system's transcription of unseen data, as well as an out-of-domain ASR system's transcriptions of audio from an unrelated task, while additionally exploring an in-between scenario when limited characterization data from the test ASR system is obtainable. To verify the extrinsic validity of the method, we also use our hallucinated ASR errors to augment training for a spoken question classifier, finding that they enable robustness to real ASR errors in a downstream task, when scarce or even zero task-specific audio was available at train-time.

* Submitted to IEEE/ACM Transactions on Audio Speech and Language Processing 

  Access Paper or Ask Questions

Fast and Robust Unsupervised Contextual Biasing for Speech Recognition

May 04, 2020
Young Mo Kang, Yingbo Zhou

Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific information or context to bias its prediction. A common framework is to dynamically construct a small language model from the provided contextual mini corpus and interpolate its score with the main language model during the decoding process. Here we propose an alternative approach that does not entail explicit contextual language model. Instead, we derive the bias score for every word in the system vocabulary from the training corpus. The method is unique in that 1) it does not require meta-data or class-label annotation for the context or the training corpus. 2) The bias score is proportional to the word's log-probability, thus not only would it bias the provided context, but also robust against irrelevant context (e.g. user mis-specified or in case where it is hard to quantify a tight scope). 3) The bias score for the entire vocabulary is pre-determined during the training stage, thereby eliminating computationally expensive language model construction during inference. We show significant improvement in recognition accuracy when the relevant context is available. Additionally, we also demonstrate that the proposed method exhibits high tolerance to false-triggering errors in the presence of irrelevant context.

* 4 pages, 1 figure 

  Access Paper or Ask Questions

The USYD-JD Speech Translation System for IWSLT 2021

Jul 24, 2021
Liang Ding, Di Wu, Dacheng Tao

This paper describes the University of Sydney& JD's joint submission of the IWSLT 2021 low resource speech translation task. We participated in the Swahili-English direction and got the best scareBLEU (25.3) score among all the participants. Our constrained system is based on a pipeline framework, i.e. ASR and NMT. We trained our models with the officially provided ASR and MT datasets. The ASR system is based on the open-sourced tool Kaldi and this work mainly explores how to make the most of the NMT models. To reduce the punctuation errors generated by the ASR model, we employ our previous work SlotRefine to train a punctuation correction model. To achieve better translation performance, we explored the most recent effective strategies, including back translation, knowledge distillation, multi-feature reranking and transductive finetuning. For model structure, we tried auto-regressive and non-autoregressive models, respectively. In addition, we proposed two novel pre-train approaches, i.e. \textit{de-noising training} and \textit{bidirectional training} to fully exploit the data. Extensive experiments show that adding the above techniques consistently improves the BLEU scores, and the final submission system outperforms the baseline (Transformer ensemble model trained with the original parallel data) by approximately 10.8 BLEU score, achieving the SOTA performance.

* IWSLT 2021 winning system of the low-resource speech translation track 

  Access Paper or Ask Questions

Deep-FSMN for Large Vocabulary Continuous Speech Recognition

Mar 04, 2018
Shiliang Zhang, Ming Lei, Zhijie Yan, Lirong Dai

In this paper, we present an improved feedforward sequential memory networks (FSMN) architecture, namely Deep-FSMN (DFSMN), by introducing skip connections between memory blocks in adjacent layers. These skip connections enable the information flow across different layers and thus alleviate the gradient vanishing problem when building very deep structure. As a result, DFSMN significantly benefits from these skip connections and deep structure. We have compared the performance of DFSMN to BLSTM both with and without lower frame rate (LFR) on several large speech recognition tasks, including English and Mandarin. Experimental results shown that DFSMN can consistently outperform BLSTM with dramatic gain, especially trained with LFR using CD-Phone as modeling units. In the 2000 hours Fisher (FSH) task, the proposed DFSMN can achieve a word error rate of 9.4% by purely using the cross-entropy criterion and decoding with a 3-gram language model, which achieves a 1.5% absolute improvement compared to the BLSTM. In a 20000 hours Mandarin recognition task, the LFR trained DFSMN can achieve more than 20% relative improvement compared to the LFR trained BLSTM. Moreover, we can easily design the lookahead filter order of the memory blocks in DFSMN to control the latency for real-time applications.

  Access Paper or Ask Questions

The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes

Jun 08, 2020
Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, Davide Testuggine

This work proposes a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. It is constructed such that unimodal models struggle and only multimodal models can succeed: difficult examples ("benign confounders") are added to the dataset to make it hard to rely on unimodal signals. The task requires subtle reasoning, yet is straightforward to evaluate as a binary classification problem. We provide baseline performance numbers for unimodal models, as well as for multimodal models with various degrees of sophistication. We find that state-of-the-art methods perform poorly compared to humans (64.73% vs. 84.7% accuracy), illustrating the difficulty of the task and highlighting the challenge that this important problem poses to the community.

  Access Paper or Ask Questions

Improving Speech Recognition for Indic Languages using Language Model

Mar 30, 2022
Ankur Dhuriya, Harveen Singh Chadha, Anirudh Gupta, Priyanshi Shah, Neeraj Chhimwal, Rishabh Gaur, Vivek Raghavan

We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec $2.0$ models for $18$ Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over $28$ \% and the average Word Error Rate (WER) decreases by about $36$ \% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high quality transcriptions can be obtained on domain-specific data without retraining the ASR model and show results on biomedical domain.

* This paper was submitted to Interspeech 2022 

  Access Paper or Ask Questions

Idea density for predicting Alzheimer's disease from transcribed speech

Jun 14, 2017
Kairit Sirts, Olivier Piguet, Mark Johnson

Idea Density (ID) measures the rate at which ideas or elementary predications are expressed in an utterance or in a text. Lower ID is found to be associated with an increased risk of developing Alzheimer's disease (AD) (Snowdon et al., 1996; Engelman et al., 2010). ID has been used in two different versions: propositional idea density (PID) counts the expressed ideas and can be applied to any text while semantic idea density (SID) counts pre-defined information content units and is naturally more applicable to normative domains, such as picture description tasks. In this paper, we develop DEPID, a novel dependency-based method for computing PID, and its version DEPID-R that enables to exclude repeating ideas---a feature characteristic to AD speech. We conduct the first comparison of automatically extracted PID and SID in the diagnostic classification task on two different AD datasets covering both closed-topic and free-recall domains. While SID performs better on the normative dataset, adding PID leads to a small but significant improvement (+1.7 F-score). On the free-topic dataset, PID performs better than SID as expected (77.6 vs 72.3 in F-score) but adding the features derived from the word embedding clustering underlying the automatic SID increases the results considerably, leading to an F-score of 84.8.

* CoNLL 2017 

  Access Paper or Ask Questions