This study explores four methods of generating paraphrases in Malayalam,
utilizing resources available for English paraphrasing and pre-trained Neural
Machine Translation (NMT) models. We evaluate the resulting paraphrases using
both automated metrics, such as BLEU, METEOR, and cosine similarity, as well as
human annotation. Our findings suggest that automated evaluation measures may
not be fully appropriate for Malayalam, as they do not consistently align with
human judgment. This discrepancy underscores the need for more nuanced
paraphrase evaluation approaches especially for highly agglutinative languages.

该研究探讨了四种生成马拉雅拉姆语释义的方法，利用了英语释义和预训练的神经机器翻译模型的资源。我们使用自动化评估指标（如 BLEU、METEOR 和余弦相似度）和人工标注来评估生成的释义。我们的发现表明，自动化评估指标可能不完全适用于马拉雅拉姆语，因为它们与人的判断不一致。这种差异凸显了对高度聚集语言特别是马拉雅拉姆语更细致的释义评估方法的需求。

马拉雅拉姆语改写生成的神经机器翻译

Neural Machine Translation for Malayalam Paraphrase Generation

In a hybrid automatic speech recognition (ASR) system, a pronunciation
lexicon (PL) and a language model (LM) are essential to correctly retrieve
spoken word sequences. Being a morphologically complex language, the vocabulary
of Malayalam is so huge and it is impossible to build a PL and an LM that cover
all diverse word forms. Usage of subword tokens to build PL and LM, and
combining them to form words after decoding, enables the recovery of many out
of vocabulary words. In this work we investigate the impact of using syllables
as subword tokens instead of words in Malayalam ASR, and evaluate the relative
improvement in lexicon size, model memory requirement and word error rate.

本文探讨了在马拉雅拉姆语自动语音识别中使用音节子单元作为音素字典和语言模型，并评估了词汇量、内存需求和词语错误率的相对改善。

使用音节子词标记进行开放词汇马拉雅拉姆语语音识别

Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

Modern text-to-speech (TTS) systems use deep learning to synthesize speech
increasingly approaching human quality, but they require a database of high
quality audio-text sentence pairs for training. Malayalam, the official
language of the Indian state of Kerala and spoken by 35+ million people, is a
low resource language in terms of available corpora for TTS systems. In this
paper, we present IMaSC, a Malayalam text and speech corpora containing
approximately 50 hours of recorded speech. With 8 speakers and a total of
34,473 text-audio pairs, IMaSC is larger than every other publicly available
alternative. We evaluated the database by using it to train TTS models for each
speaker based on a modern deep learning architecture. Via subjective
evaluation, we show that our models perform significantly better in terms of
naturalness compared to previous studies and publicly available models, with an
average mean opinion score of 4.50, indicating that the synthesized speech is
close to human quality.

本论文介绍了 IMaSC，一个包含约 50 个小时录音的马拉雅拉姆文本和语音语料库，演示使用该数据集对每位演讲者训练的 TTS 模型较以前的研究和公开可用模型表现更好，平均意见分数为 4.50。