Akifumi Yoshimoto


2024

pdf
Llama-VITS: Enhancing TTS Synthesis with Semantic Awareness
Xincan Feng | Akifumi Yoshimoto
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Recent advancements in Natural Language Processing (NLP) have seen Large-scale Language Models (LLMs) excel at producing high-quality text for various purposes. Notably, in Text-To-Speech (TTS) systems, the integration of BERT for semantic token generation has underscored the importance of semantic content in producing coherent speech outputs. Despite this, the specific utility of LLMs in enhancing TTS synthesis remains considerably limited. This research introduces an innovative approach, Llama-VITS, which enhances TTS synthesis by enriching the semantic content of text using LLM. Llama-VITS integrates semantic embeddings from Llama2 with the VITS model, a leading end-to-end TTS framework. By leveraging Llama2 for the primary speech synthesis process, our experiments demonstrate that Llama-VITS matches the naturalness of the original VITS (ORI-VITS) and those incorporate BERT (BERT-VITS), on the LJSpeech dataset, a substantial collection of neutral, clear speech. Moreover, our method significantly enhances emotive expressiveness on the EmoV_DB_bea_sem dataset, a curated selection of emotionally consistent speech from the EmoV_DB dataset, highlighting its potential to generate emotive speech.

2017

pdf
Improving Sequence to Sequence Neural Machine Translation by Utilizing Syntactic Dependency Information
An Nguyen Le | Ander Martinez | Akifumi Yoshimoto | Yuji Matsumoto
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Sequence to Sequence Neural Machine Translation has achieved significant performance in recent years. Yet, there are some existing issues that Neural Machine Translation still does not solve completely. Two of them are translation for long sentences and the “over-translation”. To address these two problems, we propose an approach that utilize more grammatical information such as syntactic dependencies, so that the output can be generated based on more abundant information. In our approach, syntactic dependencies is employed in decoding. In addition, the output of the model is presented not as a simple sequence of tokens but as a linearized tree construction. In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure. Experiments on the Europarl-v7 dataset of French-to-English translation demonstrate that our proposed method improves BLEU scores by 1.57 and 2.40 on datasets consisting of sentences with up to 50 and 80 tokens, respectively. Furthermore, the proposed method also solved the two existing problems, ineffective translation for long sentences and over-translation in Neural Machine Translation.

2016

pdf
Identification of Flexible Multiword Expressions with the Help of Dependency Structure Annotation
Ayaka Morimoto | Akifumi Yoshimoto | Akihiko Kato | Hiroyuki Shindo | Yuji Matsumoto
Proceedings of the Workshop on Grammar and Lexicon: interactions and interfaces (GramLex)

This paper presents our ongoing work on compilation of English multi-word expression (MWE) lexicon. We are especially interested in collecting flexible MWEs, in which some other components can intervene the expression such as “a number of” vs “a large number of” where a modifier of “number” can be placed in the expression and inherit the original meaning. We fiest collect possible candidates of flexible English MWEs from the web, and annotate all of their occurrences in the Wall Street Journal portion of Ontonotes corpus. We make use of word dependency strcuture information of the sentences converted from the phrase structure annotation. This process enables semi-automatic annotation of MWEs in the corpus and simultanaously produces the internal and external dependency representation of flexible MWEs.

2015

pdf
Coordination-Aware Dependency Parsing (Preliminary Report)
Akifumi Yoshimoto | Kazuo Hara | Masashi Shimbo | Yuji Matsumoto
Proceedings of the 14th International Conference on Parsing Technologies

2013

pdf
Construction of English MWE Dictionary and its Application to POS Tagging
Yutaro Shigeto | Ai Azuma | Sorami Hisamoto | Shuhei Kondo | Tomoya Kose | Keisuke Sakaguchi | Akifumi Yoshimoto | Frances Yung | Yuji Matsumoto
Proceedings of the 9th Workshop on Multiword Expressions