Public sources like parliament meeting recordings and transcripts provide ever-growing material for the training and evaluation of automatic speech recognition (ASR) systems. In this paper, we publish and analyse the Finnish parliament ASR corpus, the largest publicly available collection of manually transcribed speech data for Finnish with over 3000 hours of speech and 449 speakers for which it provides rich demographic metadata. This corpus builds on earlier initial work, and as a result the corpus has a natural split into two training subsets from two periods of time. Similarly, there are two official, corrected test sets covering different times, setting an ASR task with longitudinal distribution-shift characteristics. An official development set is also provided. We develop a complete Kaldi-based data preparation pipeline, and hidden Markov model (HMM), hybrid deep neural network (HMM-DNN) and attention-based encoder-decoder (AED) ASR recipes. We set benchmarks on the official test sets, as well as multiple other recently used test sets. Both temporal corpus subsets are already large, and we observe that beyond their scale, ASR performance on the official test sets plateaus, whereas other domains benefit from added data. The HMM-DNN and AED approaches are compared in a carefully matched equal data setting, with the HMM-DNN system consistently performing better. Finally, the variation of the ASR accuracy is compared between the speaker categories available in the parliament metadata to detect potential biases based on factors such as gender, age, and education.
An end-to-end (E2E) speech recognition model implicitly learns a biased internal language model (ILM) during training. To fused an external LM during inference, the scores produced by the biased ILM need to be estimated and subtracted. In this paper we propose two novel approaches to estimate the biased ILM based on Listen-Attend-Spell (LAS) models. The simpler method is to replace the context vector of the LAS decoder at every time step with a learnable vector. The other more advanced method is to use a simple feed-forward network to directly map query vectors to context vectors, making the generation of the context vectors independent of the LAS encoder. Both the learnable vector and the mapping network are trained on the transcriptions of the training data to minimize the perplexity while all the other parameters of the LAS model is fixed. Experiments show that the ILMs estimated by the proposed methods achieve the lowest perplexity. In addition, they also significantly outperform the shallow fusion method and two previously proposed Internal Language Model Estimation (ILME) approaches on multiple datasets.
The studies of predicting affective states from human voices have relied heavily on speech. This study, indeed, explores the recognition of humans' affective state from their vocal burst, a short non-verbal vocalization. Borrowing the idea from the recent success of wav2vec 2.0, we evaluated finetuned wav2vec 2.0 models from different datasets to predict the affective state of the speaker from their vocal burst. The finetuned wav2vec 2.0 models are then trained on the vocal burst data. The results show that the finetuned wav2vec 2.0 models, particularly on an affective speech dataset, outperform the baseline model, which is handcrafted acoustic features. However, there is no large gap between the model finetuned on non-affective speech dataset and affective speech dataset.
The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS). Although they have been widely adopted and used to tune real-world NAS algorithms, these benchmarks are limited to small search spaces and focus solely on image classification. Recently, several new NAS benchmarks have been introduced that cover significantly larger search spaces over a wide range of tasks, including object detection, speech recognition, and natural language processing. However, substantial differences among these NAS benchmarks have so far prevented their widespread adoption, limiting researchers to using just a few benchmarks. In this work, we present an in-depth analysis of popular NAS algorithms and performance prediction methods across 25 different combinations of search spaces and datasets, finding that many conclusions drawn from a few NAS benchmarks do not generalize to other benchmarks. To help remedy this problem, we introduce NAS-Bench-Suite, a comprehensive and extensible collection of NAS benchmarks, accessible through a unified interface, created with the aim to facilitate reproducible, generalizable, and rapid NAS research. Our code is available at https://github.com/automl/naslib.
Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition. Experimental results suggest that distortion-independent acoustic modeling is able to overcome the distortion problem. Such an acoustic model can also work with speech enhancement models different from the one used during training. Moreover, the models investigated in this paper outperform the previous best system on the CHiME-2 corpus.
In this paper, we explore the benefits of incorporating context into a Recurrent Neural Network (RNN-T) based Automatic Speech Recognition (ASR) model to improve the speech recognition for virtual assistants. Specifically, we use meta information extracted from the time at which the utterance is spoken and the approximate location information to make ASR context aware. We show that these contextual information, when used individually, improves overall performance by as much as 3.48% relative to the baseline and when the contexts are combined, the model learns complementary features and the recognition improves by 4.62%. On specific domains, these contextual signals show improvements as high as 11.5%, without any significant degradation on others. We ran experiments with models trained on data of sizes 30K hours and 10K hours. We show that the scale of improvement with the 10K hours dataset is much higher than the one obtained with 30K hours dataset. Our results indicate that with limited data to train the ASR model, contextual signals can improve the performance significantly.
Speech recognition systems are often highly domain dependent, a fact widely reported in the literature. However the concept of domain is complex and not bound to clear criteria. Hence it is often not evident if data should be considered to be out-of-domain. While both acoustic and language models can be domain specific, work in this paper concentrates on acoustic modelling. We present a novel method to perform unsupervised discovery of domains using Latent Dirichlet Allocation (LDA) modelling. Here a set of hidden domains is assumed to exist in the data, whereby each audio segment can be considered to be a weighted mixture of domain properties. The classification of audio segments into domains allows the creation of domain specific acoustic models for automatic speech recognition. Experiments are conducted on a dataset of diverse speech data covering speech from radio and TV broadcasts, telephone conversations, meetings, lectures and read speech, with a joint training set of 60 hours and a test set of 6 hours. Maximum A Posteriori (MAP) adaptation to LDA based domains was shown to yield relative Word Error Rate (WER) improvements of up to 16% relative, compared to pooled training, and up to 10%, compared with models adapted with human-labelled prior domain knowledge.
Acoustic modeling for child speech is challenging due to the high acoustic variability caused by physiological differences in the vocal tract. The dearth of publicly available datasets makes the task more challenging. In this work, we propose a feature adaptation approach by exploiting adversarial multi-task training to minimize acoustic mismatch at the senone (tied triphone states) level between adult and child speech and leverage large amounts of transcribed adult speech. We validate the proposed method on three tasks: child speech recognition, child pronunciation assessment, and child fluency score prediction. Empirical results indicate that our proposed approach consistently outperforms competitive baselines, achieving 7.7% relative error reduction on speech recognition and up to 25.2% relative gains on the evaluation tasks.
Automatic Speech Recognition (ASR) by machine is an attractive research topic in signal processing domain and has attracted many researchers to contribute in this area. In recent year, there have been many advances in automatic speech reading system with the inclusion of audio and visual speech features to recognize words under noisy conditions. The objective of audio-visual speech recognition system is to improve recognition accuracy. In this paper we computed visual features using Zernike moments and audio feature using Mel Frequency Cepstral Coefficients (MFCC) on vVISWa (Visual Vocabulary of Independent Standard Words) dataset which contains collection of isolated set of city names of 10 speakers. The visual features were normalized and dimension of features set was reduced by Principal Component Analysis (PCA) in order to recognize the isolated word utterance on PCA space.The performance of recognition of isolated words based on visual only and audio only features results in 63.88 and 100 respectively.
Recent natural language processing (NLP) techniques have accomplished high performance on benchmark datasets, primarily due to the significant improvement in the performance of deep learning. The advances in the research community have led to great enhancements in state-of-the-art production systems for NLP tasks, such as virtual assistants, speech recognition, and sentiment analysis. However, such NLP systems still often fail when tested with adversarial attacks. The initial lack of robustness exposed troubling gaps in current models' language understanding capabilities, creating problems when NLP systems are deployed in real life. In this paper, we present a structured overview of NLP robustness research by summarizing the literature in a systemic way across various dimensions. We then take a deep-dive into the various dimensions of robustness, across techniques, metrics, embeddings, and benchmarks. Finally, we argue that robustness should be multi-dimensional, provide insights into current research, identify gaps in the literature to suggest directions worth pursuing to address these gaps.