Abstract

We propose a Text-to-Speech method to create an unseen expressive style using one utterance of expressive speech of around one second. Specifically, we enhance the disentanglement capabilities of a state-of-the-art sequence-to-sequence based system with a Variational AutoEncoder (VAE) and a Householder Flow. The proposed system provides a 22% KLdivergence reduction while jointly improving perceptual metrics over state-of-the-art. At synthesis time we use one example of expressive style as a reference input to the encoder for generating any text in the desired style. Perceptual MUSHRA evaluations show that we can create a voice with a 9% relative naturalness improvement over standard Neural Text-toSpeech, while also improving the perceived emotional intensity (59 compared to the 55 of neutral speech). Index Terms— Text-to-speech, data efficiency, and semisupervised learning

Abstract

We present BOFFIN TTS (Bayesian Optimization For FIne-tuning Neural Text To Speech), a novel approach for few-shot speaker adaptation. Here, the task is to fine-tune a pre-trained TTS model to mimic a new speaker using a small corpus of target utterances. We demonstrate that there does not exist a one-size-fits-all adaptation strategy, with convincing synthesis requiring a corpus-specific configuration of the hyper-parameters that control fine-tuning. By using Bayesian optimization to efficiently optimize these hyper-parameter values for a target speaker, we are able to perform adaptation with an average 30% improvement in speaker similarity over standard techniques. Results indicate, across multiple corpora, that BOFFIN TTS can learn to synthesize new speakers using less than ten minutes of audio, achieving the same naturalness as produced for the speakers used to train the base model.

Abstract

Classroom response systems are an important tool in many active learning pedagogies. They support real-time feedback on student learning and promote student engagement, even in large classrooms, by allowing instructors to solicit an answer to a question from all students and show the results. Existing classroom response systems are general purpose and not tailored to the specific needs of a chemistry classroom. In particular, it is not easy to deploy molecular representations except as static images. Here we present the 3Dmol.js learning environment, a classroom response system that uses the open-source web-based 3Dmol.js JavaScript framework to provide interactive viewing and querying of 3D molecules. 3Dmol.js is available under a BSD 3-clause open-source license, and the learning-environment features are all available through http://3dmol.csb.pitt.edu/ without any software installation required. KEYWORDS: Internet/Web-Based Learning, Computer-Based Learning

Abstract

In the presence of unmodelled dynamics and uncertainties with no a priori constant bounds, conventional robust adaptation strategies for switched systems cannot allow the control gains of inactive subsystems to remain constant during inactive intervals: vanishing gains are typically required in order to prove bounded stability. As a consequence, these strategies, known in literature as leakage-based adaptive methods, might introduce poor transients at each switching instant. Leakage-based adaptive control becomes even more problematic in the switched nonlinear case, where non-conservative state-dependent upper bounds for uncertainties and unmodelled dynamics are required. This work shows that, for a class of switched Euler–Lagrange systems, such difficulties can be mitigated: a novel leakage-based stable mechanism is introduced which allows the gains of inactive subsystems to remain constant. At the same time, unmodelled dynamics and uncertainties with no a priori bounds can be handled by a quadratic state-dependent upper bound structure that reduces conservativeness as compared to state-of-the-art structures. The proposed design is validated analytically and its performance is studied in simulation with a pick-and-place robotic manipulator example.

Abstract

An index code for broadcast channel with receiver side information is locally decodable if each receiver can decode its demand by observing only a subset of the transmitted codeword symbols instead of the entire codeword. Local decodability in index coding is known to reduce receiver complexity, improve user privacy and decrease decoding error probability in wireless fading channels. Conventional index coding solutions assume that the receivers observe the entire codeword, and as a result, for these codes the number of codeword symbols queried by a user per decoded message symbol, which we refer to as locality, could be large. In this paper, we pose the index coding problem as that of minimizing the broadcast rate for a given value of locality (or vice versa) and designing codes that achieve the optimal trade-off between locality and rate. We identify the optimal broadcast rate corresponding to the minimum possible value of locality for all single unicast problems. We present new structural properties of index codes which allow us to characterize the optimal trade-off achieved by: vector linear codes when the side information graph is a directed cycle; and scalar linear codes when the minrank of the side information graph is one less than the order of the problem. We also identify the optimal trade-off among all codes, including non-linear codes, when the side information graph is a directed 3-cycle. Finally, we present techniques to design locally decodable index codes for arbitrary single unicast problems and arbitrary values of locality. Index Terms— Broadcast rate, directed cycle, index coding, linear codes, locally decodable codes, minrank.

Abstract

A fundamental essence for emotional speech analysis towards emotion recognition is a good database. Database collected from natural scenarios consists of spontaneous emotions, but there are several issues in collection of such database. Other than the privacy and legal related concerns, there is no control over environment at the background. As it is difficult to collect data from natural scenarios, many research groups have collected data from semi-natural or designed procedures. In this paper, a new emotional speech database named IIIT-H TEMD (International Institute of Information Technology-Hyderabad Telugu Emotional Database) is collected using designed drama situations from actors and non-actors. Utterances are manually annotated using a hybrid strategy by giving the context to one of the listeners. As some of the data collection studies in the literature recommend for actors, analysis of actors data versus non-actors data is carried out for their significance. The total size of the database is about 5 hours, which makes it an useful resource for the emotional speech analysis.

Abstract

Parkinson’s disease (PD) is a progressive deterioration of the human central nervous system. Detection of PD (discriminating patients with PD from healthy subjects) from speech is a useful approach due to its non-invasive nature. This study proposes to use novel cepstral coefficients derived from the single frequency filtering (SFF) method, called as single frequency filtering cepstral coefficients (SFFCCs) for the detection of PD. SFF has been shown to provide higher spectro-temporal resolution compared to the short-time Fourier transform. The current study uses the PC-GITA database, which consists of speech from speakers with PD and healthy controls (50 males, 50 females). Our proposed detection system is based on the i-vectors derived from SFFCCs using SVM as a classifier. In the detection of PD, better performance was achieved when the ivectors were computed from the proposed SFFCCs compared to the popular conventional MFCCs. Furthermore, we investigated the effect of temporal variations by deriving the shifted delta cepstral (SDC) coefficients using SFFCCs. These experiments revealed that the i-vectors derived from the proposed SFFCCs+SDC features gave an absolute improvement of 9% compared to the i-vectors derived from the baseline MFCCs+SDC features, indicating the importance of temporal variations in the

Abstract

Formants are resonances of the time varying vocal tract system, and their characteristics are reflected in the response of the system for a sequence of impulse-like excitation sequence originated at the glottis. This paper presents a method to enhance the formants information in the display of spectrogram of the speech signal, especially for high pitched voices. It is well known that in the narrowband spectrogram, the presence of pitch harmonics masks the formant information, whereas in the wideband spectrogram, the formant regions are smeared. Using single frequency filtering (SFF) analysis, we show that the wideband equivalent SFF spectrogram can be modified to enhance the formant information in the display by improving the frequency resolution. For this, we obtain two SFF spectrograms by using single frequency filtering of the speech signal at two closely spaced roots on the real axis in the z-plane. The ratio or difference of the two SFF spectrograms is processed to enhance the formant information in the spectrographic display. This will help in tracking rapidly changing formants and in resolving closely spaced formants. The effect is more pronounced in the case of high-pitched voices, like female and children speech. Keywords: formants, spectrograms, single frequency filtering

Abstract

This paper describes Naver Labs Europe’s participation in the Robustness, Chat, and Biomedical Translation tasks at WMT 2020. We propose a bidirectional German ↔ English model that is multi-domain, robust to noise, and which can translate entire documents (or bilingual dialogues) at once. We use the same ensemble of such models as our primary submission to all three tasks and achieve competitive results. We also experiment with language model pre-training techniques and evaluate their impact on robustness to noise and out-of-domain translation. For German, Spanish, Italian, and French to English translation in the Biomedical Task, we also submit our recently released multilingual Covid19NMT model.

Abstract

Word segmentation is a fundamental task for most of the NLP applications. Urdu adopts Nastalique writing style which does not have a concept of space. Furthermore, the inherent non-joining attributes of certain characters in Urdu create spaces within a word while writing in digital format. Thus, Urdu not only has space omission but also space insertion issues which make the word segmentation task challenging. In this paper, we improve upon the results of Zia, Raza and Athar (2018) by using a manually annotated corpus of 19,651 sentences along with morphological context features. Using the Conditional Random Field sequence modeler, our model achieves F1 score of 0.98 for word boundary identification and 0.92 for sub-word boundary identification tasks. The results demonstrated in this paper outperform the state-of- the-art methods.