Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality, by using domain knowledge of acoustic-phonetics. We identify temporal acoustic parameters -- such as spectral tilt, spectral flux, shimmer, etc. -- that are non-differentiable, and we develop a neural network estimator that can accurately predict their time-series values across an utterance. We also model phoneme-specific weights for each feature, as the acoustic parameters are known to show different behavior in different phonemes. We can add this criterion as an auxiliary loss to any model that produces speech, to optimize speech outputs to match the values of clean speech in these features. Experimentally we show that it improves speech enhancement workflows in both time-domain and time-frequency domain, as measured by standard evaluation metrics. We also provide an analysis of phoneme-dependent improvement on acoustic parameters, demonstrating the additional interpretability that our method provides. This analysis can suggest which features are currently the bottleneck for improvement.
While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback. In particular, phonetic feedback is rare in speech enhancement research even though it includes valuable top-down information. We use the technique of mimic loss to provide phonetic feedback to an off-the-shelf enhancement system, and find gains in objective intelligibility scores on CHiME-4 data. This technique takes a frozen acoustic model trained on clean speech to provide valuable feedbac…
Research Center for Information Technology Innovation, Academic Sinica（中央研究院资讯科技创新研究中心）；National Institute of Information and Communications Technology（国立信息与通信技术研究所）；National Chi Nan University（国立暨南国际大学）
In noisy conditions, knowing speech contents facilitates listeners to more effectively suppress background noise components and to retrieve pure speech signals. Previous studies have also confirmed the benefits of incorporating phonetic information in a speech enhancement (SE) system to achieve better denoising performance. To obtain the phonetic information, we usually prepare a phoneme-based acoustic model, which is trained using speech waveforms and phoneme labels. Despite performing well in normal noisy conditions, when operating in very noisy conditions, however, the recognized phonemes m…
Many mispronunciation detection and diagnosis (MD&D) research approaches try to exploit both the acoustic and linguistic features as input. Yet the improvement of the performance is limited, partially due to the shortage of large amount annotated training data at the phoneme level. Phonetic embeddings, extracted from ASR models trained with huge amount of word level annotations, can serve as a good representation of the content of input speech, in a noise-robust and speaker-independent manner. These embeddings, when used as implicit phonetic supplementary information, can alleviate the data sh…
Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Chi Mei Hospital（奇美医院）；National Chi Nan University（国立暨南国际大学）；Carnegie Mellon University（卡内基梅隆大学）
Rethinking Speech Representation Aggregation in Speech Enhancement: A Phonetic Mutual Information Perspective
Department of Intelligence and Information, Seoul National University, Republic of Korea（智能与信息系，首尔国立大学，韩国）；Artificial Intelligence Institute, Seoul National University, Republic of Korea（人工智能研究所，首尔国立大学，韩国）
University of Pennsylvania（宾夕法尼亚大学）；Linguistic Data Consortium, University of Pennsylvania（宾夕法尼亚大学语言数据联盟）
Pre-trained acoustic representations such as wav2vec and DeCoAR have attained impressive word error rates (WER) for speech recognition benchmarks, particularly when labeled data is limited. But little is known about what phonetic properties these various representations acquire, and how well they encode transferable features of speech. We compare features from two conventional and four pre-trained systems in some simple frame-level phonetic classification tasks, with classifiers trained on features from one version of the TIMIT dataset and tested on features from another. All contextualized re…
Researches have shown accent classification can be improved by integrating semantic information into pure acoustic approach. In this work, we combine phonetic knowledge, such as vowels, with enhanced acoustic features to build an improved accent classification system. The classifier is based on Gaussian Mixture Model-Universal Background Model (GMM-UBM), with normalized Perceptual Linear Predictive (PLP) features. The features are further optimized by Principle Component Analysis (PCA) and Hetroscedastic Linear Discriminant Analysis (HLDA). Using 7 major types of accented speech from the Forei…
State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as the mapping from the written form to the spoken form is complicated. However, in recent years the representational power of deep-learning based acoustic models has improved, raising interest in graphemic acoustic models for English, due to the simplicity of generating the lexicon. In this paper, phonetic and graphemic models are compared for an English Multi-Genre Broadcast transcription task. A range of acoustic mo…
Most speech recognition tasks pertain to mapping words across two modalities: acoustic and orthographic. In this work, we suggest learning encoders that map variable-length, acoustic or phonetic, sequences that represent words into fixed-dimensional vectors in a shared latent space; such that the distance between two word vectors represents how closely the two words sound. Instead of directly learning the distances between word vectors, we employ weak supervision and model a binary classification task to predict whether two inputs, one of each modality, represent the same word given a distance…
Korea Advanced Institute of Science and Technology（韩国科学技术院）
Previous researches on acoustic word embeddings used in query-by-example spoken term detection have shown remarkable performance improvements when using a triplet network. However, the triplet network is trained using only a limited information about acoustic similarity between words. In this paper, we propose a novel architecture, phonetically associated triplet network (PATN), which aims at increasing discriminative power of acoustic word embeddings by utilizing phonetic information as well as word identity. The proposed model is learned to minimize a combined loss function that was made by …
In spoken language understanding (SLU), what the user says is converted to his/her intent. Recent work on end-to-end SLU has shown that accuracy can be improved via pre-training approaches. We revisit ideas presented by Lugosch et al. using speech pre-training and three-module modeling; however, to ease construction of the end-to-end SLU model, we use as our phoneme module an open-source acoustic-phonetic model from a DNN-HMM hybrid automatic speech recognition (ASR) system instead of training one from scratch. Hence we fine-tune on speech only for the word module, and we apply multi-target le…
Human Language Technology and Pattern Recognition Group, RWTH Aachen University（亚琛工业大学人类语言技术与模式识别组）；AppTek GmbH（AppTek 公司）
In this work, we show that a factored hybrid hidden Markov model (FH-HMM) which is defined without any phonetic state-tying outperforms a state-of-the-art hybrid HMM. The factored hybrid HMM provides a link to transducer models in the way it models phonetic (label) context while preserving the strict separation of acoustic and language model of the hybrid HMM approach. Furthermore, we show that the factored hybrid model can be trained from scratch without using phonetic state-tying in any of the training steps. Our modeling approach enables triphone context while avoiding phonetic state-tying …
Previous accent classification research focused mainly on detecting accents with pure acoustic information without recognizing accented speech. This work combines phonetic knowledge such as vowels with acoustic information to build Guassian Mixture Model (GMM) classifier with Perceptual Linear Predictive (PLP) features, optimized by Hetroscedastic Linear Discriminant Analysis (HLDA). With input about 20-second accented speech, this system achieves classification rate of 51% on a 7-way classification system focusing on the major types of accents in English, which is competitive to the state-of-…
The performance of voice-controlled systems is usually influenced by accented speech. To make these systems more robust, the frontend accent recognition (AR) technologies have received increased attention in recent years. As accent is a high-level abstract feature that has a profound relationship with the language knowledge, AR is more challenging than other language-agnostic audio classification tasks. In this paper, we use an auxiliary automatic speech recognition (ASR) task to extract language-related phonetic features. Furthermore, we propose a hybrid structure that incorporates the embedd…
Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根-纽伦堡大学）；Universidad de Antioquia（安蒂奥基亚大学）
Current state of the art acoustic models can easily comprise more than 100 million parameters. This growing complexity demands larger training datasets to maintain a decent generalization of the final decision function. An ideal dataset is not necessarily large in size, but large with respect to the amount of unique speakers, utilized hardware and varying recording conditions. This enables a machine learning model to explore as much of the domain-specific input space as possible during parameter estimation. This work introduces Common Phone, a gender-balanced, multilingual corpus recorded from…
Phonetic Error Analysis of Raw Waveform Acoustic Models
Centre for Speech Technology Research (CSTR), University of Edinburgh, UK（语音技术研究中心（CSTR），爱丁堡大学，英国）；Cisco, UK（思科公司，英国）；SLAI & CUHK-SZ, China（SLAI与CUHK-SZ，中国）；King's College London, UK（伦敦国王学院，英国）
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling, pronunciation lexicon, and language modeling, the end-to-end paradigm is both conceptually simpler and has the potential benefit of training the entire system on the end task. However, such neural network models are more opaque: it is not clear how to interpret the role of different parts of the network and what information it learns during training. In this pape…
Technische Hochschule Nürnberg Georg Simon Ohm（纽伦堡乔治·西蒙·欧姆应用科学大学）；Intel Labs（英特尔实验室）
This work aims to automatically evaluate whether the language development of children is age-appropriate. Validated speech and language tests are used for this purpose to test the auditory memory. In this work, the task is to determine whether spoken nonwords have been uttered correctly. We compare different approaches that are motivated to model specific language structures: Low-level features (FFT), speaker embeddings (ECAPA-TDNN), grapheme-motivated embeddings (wav2vec 2.0), and phonetic embeddings in form of senones (ASR acoustic model). Each of the approaches provides input for VGG-like 5…
ENS（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；EHESS（社会科学高等学院）；INRIA（法国国家信息与自动化研究所）；University of Paris（巴黎大学）；University of Toronto（多伦多大学）
Our native language influences the way we perceive speech sounds, affecting our ability to discriminate non-native sounds. We compare two ideas about the influence of the native language on speech perception: the Perceptual Assimilation Model, which appeals to a mental classification of sounds into native phoneme categories, versus the idea that rich, fine-grained phonetic representations tuned to the statistics of the native language, are sufficient. We operationalize this idea using representations from two state-of-the-art speech models, a Dirichlet process Gaussian mixture model and the mo…
Phoneme-based acoustic modeling of large vocabulary automatic speech recognition takes advantage of phoneme context. The large number of context-dependent (CD) phonemes and their highly varying statistics require tying or smoothing to enable robust training. Usually, classification and regression trees are used for phonetic clustering, which is standard in hidden Markov model (HMM)-based systems. However, this solution introduces a secondary training objective and does not allow for end-to-end training. In this work, we address a direct phonetic context modeling for the hybrid deep neural netw…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息科技创新研究中心）
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained…
University of Science and Technology of China（中国科学技术大学）；iFLYTEK Research（科大讯飞研究院）
This paper proposes a multilingual speech synthesis method which combines unsupervised phonetic representations (UPR) and supervised phonetic representations (SPR) to avoid reliance on the pronunciation dictionaries of target languages. In this method, a pretrained wav2vec 2.0 model is adopted to extract UPRs and a language-independent automatic speech recognition (LI-ASR) model is built with a connectionist temporal classification (CTC) loss to extract segment-level SPRs from the audio data of target languages. Then, an acoustic model is designed, which first predicts UPRs and SPRs from texts…
Conventional speech enhancement technique such as beamforming has known benefits for far-field speech recognition. Our own work in frequency-domain multi-channel acoustic modeling has shown additional improvements by training a spatial filtering layer jointly within an acoustic model. In this paper, we further develop this idea and use frequency aligned network for robust multi-channel automatic speech recognition (ASR). Unlike an affine layer in the frequency domain, the proposed frequency aligned component prevents one frequency bin influencing other frequency bins. We show that this modific…
STMS UMR9912, Ircam/CNRS/SU（STMS UMR9912，Ircam/CNRS/SU）；LTCI, Institut Polytechnique de Paris（巴黎理工学院 LTCI）
Informed source separation has recently gained renewed interest with the introduction of neural networks and the availability of large multitrack datasets containing both the mixture and the separated sources. These approaches use prior information about the target source to improve separation. Historically, Music Information Retrieval researchers have focused primarily on score-informed source separation, but more recent approaches explore lyrics-informed source separation. However, because of the lack of multitrack datasets with time-aligned lyrics, models use weak conditioning with non-alig…
In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training has been proposed as a way to improve both supervised and unsupervised speech recognition, including frame-level feature representations and Acoustic Word Embeddings (AWE) for variable-length segments. However, self-supervised models alone cannot learn perfect separation of the linguistic content as they are trained to optimize indirect objectives. In this wo…
Xinjiang University（新疆大学）；Tencent Minority-Mandarin Translation（腾讯民族语言-普通话翻译团队）；Xinjiang Key Laboratory of Multi-lingual Information Technology（新疆多语种信息技术重点实验室）
Consonant and vowel reduction are often encountered in speech, which might cause performance degradation in automatic speech recognition (ASR). Our recently proposed learning strategy based on masking, Phone Masking Training (PMT), alleviates the impact of such phenomenon in Uyghur ASR. Although PMT achieves remarkably improvements, there still exists room for further gains due to the granularity mismatch between the masking unit of PMT (phoneme) and the modeling unit (word-piece). To boost the performance of PMT, we propose multi-modeling unit training (MMUT) architecture fusion with PMT (PM-…
Soochow University（苏州大学）；ByteDance AI Lab（字节跳动人工智能实验室）
Recently, phonetic posteriorgrams (PPGs) based methods have been quite popular in non-parallel singing voice conversion systems. However, due to the lack of acoustic information in PPGs, style and naturalness of the converted singing voices are still limited. To solve these problems, in this paper, we utilize an acoustic reference encoder to implicitly model singing characteristics. We experiment with different auxiliary features, including mel spectrograms, HuBERT, and the middle hidden feature (PPG-Mid) of pretrained automatic speech recognition (ASR) model, as the input of the reference enc…
Stanford University（斯坦福大学）；Stanford School of Medicine（斯坦福大学医学院）
In this paper, we propose a method for removing linguistic information from speech for the purpose of isolating paralinguistic indicators of affect. The immediate utility of this method lies in clinical tests of sensitivity to vocal affect that are not confounded by language, which is impaired in a variety of clinical populations. The method is based on simultaneous recordings of speech audio and electroglottographic (EGG) signals. The speech audio signal is used to estimate the average vocal tract filter response and amplitude envelop. The EGG signal supplies a direct correlate of voice sourc…
National Institute of Information and Communications Technology (NICT)（国立信息与通信技术研究所）
The acoustic and linguistic features are important cues for the spoken language identification (LID) task. Recent advanced LID systems mainly use acoustic features that lack the usage of explicit linguistic feature encoding. In this paper, we propose a novel transducer-based language embedding approach for LID tasks by integrating an RNN transducer model into a language embedding framework. Benefiting from the advantages of the RNN transducer's linguistic representation capability, the proposed method can exploit both phonetically-aware acoustic features and explicit linguistic features for LI…
Music Technology Group, Universitat Pompeu Fabra（庞培法布拉大学音乐技术小组）
We propose a sequence-to-sequence singing synthesizer, which avoids the need for training data with pre-aligned phonetic and acoustic features. Rather than the more common approach of a content-based attention mechanism combined with an autoregressive decoder, we use a different mechanism suitable for feed-forward synthesis. Given that phonetic timings in singing are highly constrained by the musical score, we derive an approximate initial alignment with the help of a simple duration model. Then, using a decoder based on a feed-forward variant of the Transformer model, a series of self-attenti…
Acoustic word embeddings (AWEs) are discriminative representations of speech segments, and learned embedding space reflects the phonetic similarity between words. With multi-view learning, where text labels are considered as supplementary input, AWEs are jointly trained with acoustically grounded word embeddings (AGWEs). In this paper, we expand the multi-view approach into a proxy-based framework for deep metric learning by equating AGWEs with proxies. A simple modification in computing the similarity matrix allows the general pair weighting to formulate the data-to-proxy relationship. Under …
Grapheme-based acoustic modeling has recently been shown to outperform phoneme-based approaches in both hybrid and end-to-end automatic speech recognition (ASR), even on non-phonemic languages like English. However, graphemic ASR still has problems with rare long-tail words that do not follow the standard spelling conventions seen in training, such as entity names. In this work, we present a novel method to train a statistical grapheme-to-grapheme (G2G) model on text-to-speech data that can rewrite an arbitrary character sequence into more phonetically consistent forms. We show that using G2G …
Stellenbosch University（斯泰伦博斯大学）；The University of Edinburgh（爱丁堡大学）
For our submission to the ZeroSpeech 2019 challenge, we apply discrete latent-variable neural networks to unlabelled speech and use the discovered units for speech synthesis. Unsupervised discrete subword modelling could be useful for studies of phonetic category learning in infants or in low-resource speech technology requiring symbolic input. We use an autoencoder (AE) architecture with intermediate discretisation. We decouple acoustic unit discovery from speaker modelling by conditioning the AE's decoder on the training speaker identity. At test time, unit discovery is performed on speech f…
Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
The use of phonological features (PFs) potentially allows language-specific phones to remain linked in training, which is highly desirable for information sharing for multilingual and crosslingual speech recognition methods for low-resourced languages. A drawback suffered by previous methods in using phonological features is that the acoustic-to-PF extraction in a bottom-up way is itself difficult. In this paper, we propose to join phonology driven phone embedding (top-down) and deep neural network (DNN) based acoustic feature extraction (bottom-up) to calculate phone probabilities. The new me…
Quality of data plays an important role in most deep learning tasks. In the speech community, transcription of speech recording is indispensable. Since the transcription is usually generated artificially, automatically finding errors in manual transcriptions not only saves time and labors but benefits the performance of tasks that need the training process. Inspired by the success of hybrid automatic speech recognition using both language model and acoustic model, two approaches of automatic error detection in the transcriptions have been explored in this work. Previous study using a biased la…
