Zerospeech synthesis is the task of building vocabulary independent speech synthesis systems, where transcriptions are not available for training data. It is, therefore, necessary to convert training data into a sequence of fundamental acoustic units that can be used for synthesis during the test. This paper attempts to discover, and model perceptual acoustic units consisting of steady-state, and transient regions in speech. The transients roughly correspond to CV, VC units, while the steady-state corresponds to sonorants and fricatives. The speech signal is first preprocessed by segmenting the same into CVC-like units using a short-term energy-like contour. These CVC segments are clustered using a connected components-based graph clustering technique. The clustered CVC segments are initialized such that the onset (CV) and decays (VC) correspond to transients, and the rhyme corresponds to steady-states. Following this initialization, the units are allowed to re-organise on the continuous speech into a final set of AUs in an HMM-GMM framework. AU sequences thus obtained are used to train synthesis models. The performance of the proposed approach is evaluated on the Zerospeech 2019 challenge database. Subjective and objective scores show that reasonably good quality synthesis with low bit rate encoding can be achieved using the proposed AUs.
The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（多模态人工智能系统国家重点实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Department of Automation, Tsinghua University（清华大学自动化系）；BNRist, Tsinghua University（清华大学BNRist）
Northwestern Polytechnical University（西北工业大学）；Bytedance AI Lab（字节跳动人工智能实验室）
Attention-based sequence-to-sequence (seq2seq) speech synthesis has achieved extraordinary performance. But a studio-quality corpus with manual transcription is necessary to train such seq2seq systems. In this paper, we propose an approach to build high-quality and stable seq2seq based speech synthesis system using challenging found data, where training speech contains noisy interferences (acoustic noise) and texts are imperfect speech recognition transcripts (textual noise). To deal with text-side noise, we propose a VQVAE based heuristic method to compensate erroneous linguistic feature with…
Text-to-Speech synthesis systems are generally evaluated using Mean Opinion Score (MOS) tests, where listeners score samples of synthetic speech on a Likert scale. A major drawback of MOS tests is that they only offer a general measure of overall quality-i.e., the naturalness of an utterance-and so cannot tell us where exactly synthesis errors occur. This can make evaluation of the appropriateness of prosodic variation within utterances inconclusive. To address this, we propose a novel evaluation method based on the Rapid Prosody Transcription paradigm. This allows listeners to mark the locati…
This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the "artistic intention". Towards assessing this distinction, we carried out an experimental evaluation where 91 subjects were invited to listen to various audio recordings created by resynthesizing MIDI data obtained through Automatic Music Transcription (AMT) systems and a sensorized acoustic piano. During the resynthesis, we simulated different contexts and a…
We propose a system that transcribes the conversation of a typical meeting scenario that is captured by a set of initially unsynchronized microphone arrays at unknown positions. It consists of subsystems for signal synchronization, including both sampling rate and sampling time offset estimation, diarization based on speaker and microphone array position estimation, multi-channel speech enhancement, and automatic speech recognition. With the estimated diarization information, a spatial mixture model is initialized that is used to estimate beamformer coefficients for source separation. Simulati…
Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of perceptual losses. Perceptual loss discourages distortion to certain speech properties and we analyze it using six large-scale pre-trained models: speaker classification, acoustic model, speaker embedding, emotion classification, and two self-supervised speech encoders (PASE+, wav2vec 2.0). We first build a strong baseline (w/o PERL) using Conformer Transformer N…
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…
Speech enhancement models have greatly progressed in recent years, but still show limits in perceptual quality of their speech outputs. We propose an objective for perceptual quality based on temporal acoustic parameters. These are fundamental speech features that play an essential role in various applications, including speaker recognition and paralinguistic analysis. We provide a differentiable estimator for four categories of low-level acoustic descriptors involving: frequency-related parameters, energy or amplitude-related parameters, spectral balance parameters, and temporal features. Unl…
Deep acoustic models represent linguistic information based on massive amounts of data. Unfortunately, for regional languages and dialects such resources are mostly not available. However, deep acoustic models might have learned linguistic information that transfers to low-resource languages. In this study, we evaluate whether this is the case through the task of distinguishing low-resource (Dutch) regional varieties. By extracting embeddings from the hidden layers of various wav2vec 2.0 models (including new models which are pre-trained and/or fine-tuned on Dutch) and using dynamic time warpi…
In this paper, we propose to improve emotion recognition by combining acoustic information and conversation transcripts. On the one hand, an LSTM network was used to detect emotion from acoustic features like f0, shimmer, jitter, MFCC, etc. On the other hand, a multi-resolution CNN was used to detect emotion from word sequences. This CNN consists of several parallel convolutions with different kernel sizes to exploit contextual information at different levels. A temporal pooling layer aggregates the hidden representations of different words into a unique sequence level embedding, from which we…
In this paper, we present a method for fine-tuning models trained on the Deep Noise Suppression (DNS) 2020 Challenge to improve their performance on Voice over Internet Protocol (VoIP) applications. Our approach involves adapting the DNS 2020 models to the specific acoustic characteristics of VoIP communications, which includes distortion and artifacts caused by compression, transmission, and platform-specific processing. To this end, we propose a multi-task learning framework for VoIP-DNS that jointly optimizes noise suppression and VoIP-specific acoustics for speech enhancement. We evaluate …
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…
End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to integrate with downstream tasks such as spoken language understanding, because inference (search) is much simplified compared to phoneme, character or any other sort of sub-word units. In this paper, we describe methods to construct contextual acoustic word embeddings directly from a supervised sequence-to-sequence acoustic-to-word speech recognition model …
Every sound that we hear is the result of successive convolutional operations (e.g. room acoustics, microphone characteristics, resonant properties of the instrument itself, not to mention characteristics and limitations of the sound reproduction system). In this work we seek to determine the best room in which to perform a particular piece using AI. Additionally, we use room acoustics as a way to enhance the perceptual qualities of a given sound. Historically, rooms (particularly Churches and concert halls) were designed to host and serve specific musical functions. In some cases the architec…
University of Michigan（密歇根大学）；Northwestern University（西北大学）
Speech is a critical biomarker for Huntington Disease (HD), with changes in speech increasing in severity as the disease progresses. Speech analyses are currently conducted using either transcriptions created manually by trained professionals or using global rating scales. Manual transcription is both expensive and time-consuming and global rating scales may lack sufficient sensitivity and fidelity. Ultimately, what is needed is an unobtrusive measure that can cheaply and continuously track disease progression. We present first steps towards the development of such a system, demonstrating the …
New Advances in machine learning have made Automated Speech Recognition (ASR) systems practical and more scalable. These systems, however, pose serious privacy threats as speech is a rich source of sensitive acoustic and textual information. Although offline and open-source ASR eliminates the privacy risks, its transcription performance is inferior to that of cloud-based ASR systems, especially for real-world use cases. In this paper, we propose Pr$εε$ch, an end-to-end speech transcription system which lies at an intermediate point in the privacy-utility spectrum. It protects the acoustic feat…
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 aco…
We present an analysis of semi-supervised acoustic and language model training for English-isiZulu code-switched ASR using soap opera speech. Approximately 11 hours of untranscribed multilingual speech was transcribed automatically using four bilingual code-switching transcription systems operating in English-isiZulu, English-isiXhosa, English-Setswana and English-Sesotho. These transcriptions were incorporated into the acoustic and language model training sets. Results showed that the TDNN-F acoustic models benefit from the additional semi-supervised data and that even better performance coul…
We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support humanitarian relief programmes in rural Africa. Using just 1.57 hours of annotated speech data as a seed corpus, we increase the pool of training data by applying semi-supervised training to 17.55 hours of untranscribed speech. We make use of factorised time-delay neural networks (TDNN-F) for acoustic modelling, since these have recently been shown to be effect…
In this paper, we propose a novel approach for the transcription of speech conversations with natural speaker overlap, from single channel speech recordings. The proposed model is a combination of a speaker diarization system and a hybrid automatic speech recognition (ASR) system. The speaker conditioned acoustic model (SCAM) in the ASR system consists of a series of embedding layers which use the speaker activity inputs from the diarization system to derive speaker specific embeddings. The output of the SCAM are speaker specific senones that are used for decoding the transcripts for each spea…
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to deal with errors by ASR. Moreover, there are acoustic features which are related with intents but not represented with the transcripts. In this paper, we present an end-to-end model which directly converts speech into dialog acts without the deterministic transcription process. In the proposed model, the dialog act recognition network is conjunct with an acoust…
University of Augsburg（奥格斯堡大学）；Huawei Technologies（华为技术有限公司）；HSE University（俄罗斯国家研究型高等经济大学）；ITMO University（圣彼得堡国立信息技术机械与光学大学）；Imperial College London（伦敦帝国理工学院）
Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the SER systems. Further, more clarification is required for analysing the impact of ASR's word error rate (WER) on linguistic emotion recognition per se and in the context of fusion with acoustic information exploitation in the age of deep ASR systems. In order to tackle the above issues, we create transcripts from the original speech by applying three modern AS…
University of Erlangen-Nuremberg（埃尔朗根-纽伦堡大学）；International Audio Laboratories（国际音频实验室）
Previous DCASE challenges contributed to an increase in the performance of acoustic scene classification systems. State-of-the-art classifiers demand significant processing capabilities and memory which is challenging for resource-constrained mobile or IoT edge devices. Thus, it is more likely to deploy these models on more powerful hardware and classify audio recordings previously uploaded (or streamed) from low-power edge devices. In such scenario, the edge device may apply perceptual audio coding to reduce the transmission data rate. This paper explores the effect of perceptual audio coding…
Toshiba Cambridge Research Laboratory（东芝剑桥研究实验室）；Paderborn University（帕德博恩大学）
Despite the strong modeling power of neural network acoustic models, speech enhancement has been shown to deliver additional word error rate improvements if multi-channel data is available. However, there has been a longstanding debate whether enhancement should also be carried out on the ASR training data. In an extensive experimental evaluation on the acoustically very challenging CHiME-5 dinner party data we show that: (i) cleaning up the training data can lead to substantial error rate reductions, and (ii) enhancement in training is advisable as long as enhancement in test is at least as s…
National Engineering Laboratory for Speech and Language Information Processing（国家语音与语言信息处理工程实验室）；University of Science and Technology of China（中国科学技术大学）
Batch normalization (BN) is an effective method to accelerate model training and improve the generalization performance of neural networks. In this paper, we propose an improved batch normalization technique called attentive batch normalization (ABN) in Long Short Term Memory (LSTM) based acoustic modeling for automatic speech recognition (ASR). In the proposed method, an auxiliary network is used to dynamically generate the scaling and shifting parameters in batch normalization, and attention mechanisms are introduced to improve their regularized performance. Furthermore, two schemes, frame-l…
Singing voice synthesis has been paid rising attention with the rapid development of speech synthesis area. In general, a studio-level singing corpus is usually necessary to produce a natural singing voice from lyrics and music-related transcription. However, such a corpus is difficult to collect since it's hard for many of us to sing like a professional singer. In this paper, we propose an approach -- Learn2Sing that only needs a singing teacher to generate the target speakers' singing voice without their singing voice data. In our approach, a teacher's singing corpus and speech from multiple…
Stanford University（斯坦福大学）；MIT Lincoln Laboratory（麻省理工学院林肯实验室）；Worcester Polytechnic Institute（伍斯特理工学院）；Mass General Hospital（麻省总医院）；University of Texas at Dallas（德克萨斯大学达拉斯分校）
Recommendations for common outcome measures following pediatric traumatic brain injury (TBI) support the integration of instrumental measurements alongside perceptual assessment in recovery and treatment plans. A comprehensive set of sensitive, robust and non-invasive measurements is therefore essential in assessing variations in speech characteristics over time following pediatric TBI. In this article, we study the changes in the acoustic speech patterns of a pediatric cohort of ten subjects diagnosed with severe TBI. We extract a diverse set of both well-known and novel acoustic features fro…
Johns Hopkins University（约翰霍普金斯大学）；Renmin University of China（中国人民大学）
The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high data acquisition and annotation costs. In this work, we propose a Perceptual Entropy (PE) loss derived from a psycho-acoustic hearing model to regularize the network. With a one-hour open-source singing voice database, we explore the impact of the PE loss on various mainstream sequence-to-sequence models, including the RNN-based, transformer-based,…
The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of practical significance in many applications of speech analytics, including those concerning low-resource languages, and large amount of multilingual and multi-genre data. We propose a two-stage approach, which comprises unsupervised acoustic modeling and decoding, followed by pattern mining in acoustic unit sequences. The whole process starts by deriving and mo…
Hearing Like Humans? Sound Symbolism and Perceptual Alignment in Speech Language Models
Graduate Institute of Communication Engineering National Taiwan University Taipei, Taiwan；Graduate Institute of Electrical Engineering National Taiwan University Taipei, Taiwan；Artificial Intelligence Center of Research Excellence National Taiwan University Taipei, Taiwan
The Unreliability of Acoustic Systems in Alzheimer's Speech Datasets with Heterogeneous Recording Conditions
Instituto de Investigación en Ciencias de la Computación, UBA-CONICET（布宜诺斯艾利斯大学-国家科学技术研究委员会计算机科学研究所）；Departamento de Computación, Facultad de Ciencias Exactas y Naturales, UBA（布宜诺斯艾利斯大学精确与自然科学学院计算机系）；Centro de Neurociencias Cognitivas, Universidad de San Andrés（圣安德烈斯大学认知神经科学中心）
Despite improved performances of the latest Automatic Speech Recognition (ASR) systems, transcription errors are still unavoidable. These errors can have a considerable impact in critical domains such as healthcare, when used to help with clinical documentation. Therefore, detecting ASR errors is a critical first step in preventing further error propagation to downstream applications. To this end, we propose a novel end-to-end approach for ASR error detection using audio-transcript entailment. To the best of our knowledge, we are the first to frame this problem as an end-to-end entailment task…
