A Pilot Study of Applying Sequence-to-Sequence Voice Conversion to Evaluate the Intelligibility of L2 Speech Using a Native Speaker's Shadowings

Utterances by L2 speakers can be unintelligible due to mispronunciation and improper prosody. In computer-aided language learning systems, textual feedback is often provided using a speech recognition engine. However, an ideal form of feedback for L2 speakers should be so fine-grained that it enables them to detect and diagnose unintelligible parts of L2 speakers' utterances. Inspired by language teachers who correct students' pronunciation through a voice-to-voice process, this pilot study utilizes a unique semi-parallel dataset composed of non-native speakers' (L2) reading aloud, shadowing of native speakers (L1) and their script-shadowing utterances. We explore the technical possibility of replicating the process of an L1 speaker's shadowing L2 speech using Voice Conversion techniques, to create a virtual shadower system. Experimental results demonstrate the feasibility of the VC system in simulating L1's shadowing behavior. The output of the virtual shadower system shows a reasonable similarity to the real L1 shadowing utterances in both linguistic and acoustic aspects.

Simulating Native Speaker Shadowing for Nonnative Speech Assessment with Latent Speech Representations

Evaluating speech intelligibility is a critical task in computer-aided language learning systems. Traditional methods often rely on word error rates (WER) provided by automatic speech recognition (ASR) as intelligibility scores. However, this approach has significant limitations due to notable differences between human speech recognition (HSR) and ASR. A promising alternative is to involve a native (L1) speaker in shadowing what nonnative (L2) speakers say. Breakdowns or mispronunciations in the L1 speaker's shadowing utterance can serve as indicators for assessing L2 speech intelligibility. In this study, we propose a speech generation system that simulates the L1 shadowing process using voice conversion (VC) techniques and latent speech representations. Our experimental results demonstrate that this method effectively replicates the L1 shadowing process, offering an innovative tool to evaluate L2 speech intelligibility. Notably, systems that utilize self-supervised speech representations (S3R) show a higher degree of similarity to real L1 shadowing utterances in both linguistic accuracy and naturalness.

A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora

We propose a method of simulating the human process of foreign accentuation using Generative Spoken Language Model (GSLM) only with native speech corpora. When one listens to spoken words of a foreign language and repeats them, the repeated speech is often with the accent of that listener's L1. This is said to be because the spoken words are mentally represented as a sequence of phonological units of the L1, and those units are used for oral reproduction. We simulate this process by inputting speech of language A into GSLM of language B to add B's accent onto the input speech. The process of running ASR of the L1 for foreign input speech and giving the ASR result to TTS of the L1 can be viewed as a naive implementation of this approach. The results of our experiments show that the synthesized accent of the output speech is highly natural, compared to real samples of A generated by speakers whose L1 is B, and that the degree of accentuation is controllable.

Exploring Isolated Musical Notes as Pre-training Data for Predominant Instrument Recognition in Polyphonic Music

With the growing amount of musical data available, automatic instrument recognition, one of the essential problems in Music Information Retrieval (MIR), is drawing more and more attention. While automatic recognition of single instruments has been well-studied, it remains challenging for polyphonic, multi-instrument musical recordings. This work presents our efforts toward building a robust end-to-end instrument recognition system for polyphonic multi-instrument music. We train our model using a pre-training and fine-tuning approach: we use a large amount of monophonic musical data for pre-training and subsequently fine-tune the model for the polyphonic ensemble. In pre-training, we apply data augmentation techniques to alleviate the domain gap between monophonic musical data and real-world music. We evaluate our method on the IRMAS testing data, a polyphonic musical dataset comprising professionally-produced commercial music recordings. Experimental results show that our best model achieves a micro F1-score of 0.674 and an LRAP of 0.814, meaning 10.9% and 8.9% relative improvement compared with the previous state-of-the-art end-to-end approach. Also, we are able to build a lightweight model, achieving competitive performance with only 519K trainable parameters.

Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition

Low resource speech recognition has been long-suffering from insufficient training data. While neighbour languages are often used as assistant training data, it would be difficult for the model to induct similar units (character, subword, etc.) across the languages. In this paper, we assume similar units in neighbour language share similar term frequency and form a Huffman tree to perform multi-lingual hierarchical Softmax decoding. During decoding, the hierarchical structure can benefit the training of low-resource languages. Experimental results show the effectiveness of our method.

Wasserstein GAN and Waveform Loss-based Acoustic Model Training for Multi-speaker Text-to-Speech Synthesis Systems Using a WaveNet Vocoder

Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech synthesis systems. Such neural networks are being used as an alternative to vocoders and hence they are often called neural vocoders. The neural vocoder uses acoustic features as local condition parameters, and these parameters need to be accurately predicted by another acoustic model. However, it is not yet clear how to train this acoustic model, which is problematic because the final quality of synthetic speech is significantly affected by the performance of the acoustic model. Significant degradation happens, especially when predicted acoustic features have mismatched characteristics compared to natural ones. In order to reduce the mismatched characteristics between natural and generated acoustic features, we propose frameworks that incorporate either a conditional generative adversarial network (GAN) or its variant, Wasserstein GAN with gradient penalty (WGAN-GP), into multi-speaker speech synthesis that uses the WaveNet vocoder. We also extend the GAN frameworks and use the discretized mixture logistic loss of a well-trained WaveNet in addition to mean squared error and adversarial losses as parts of objective functions. Experimental results show that acoustic models trained using the WGAN-GP framework using back-propagated discretized-mixture-of-logistics (DML) loss achieves the highest subjective evaluation scores in terms of both quality and speaker similarity.