Handwritten character recognition is a crucial task because of its abundant applications. The recognition task of Bangla handwritten characters is especially challenging because of the cursive nature of Bangla characters and the presence of compound characters with more than one way of writing. In this paper, a classification model based on the ensembling of several Convolutional Neural Networks (CNN), namely, BanglaNet is proposed to classify Bangla basic characters, compound characters, numerals, and modifiers. Three different models based on the idea of state-of-the-art CNN models like Inception, ResNet, and DenseNet have been trained with both augmented and non-augmented inputs. Finally, all these models are averaged or ensembled to get the finishing model. Rigorous experimentation on three benchmark Bangla handwritten characters datasets, namely, CMATERdb, BanglaLekha-Isolated, and Ekush has exhibited significant recognition accuracies compared to some recent CNN-based research. The top-1 recognition accuracies obtained are 98.40%, 97.65%, and 97.32%, and the top-3 accuracies are 99.79%, 99.74%, and 99.56% for CMATERdb, BanglaLekha-Isolated, and Ekush datasets respectively.

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-context learning capabilities and naturalness. However, control of speaker identity and style in these models typically requires conditioning on reference speech recordings, limiting creative applications. Alternatively, natural language prompting of speaker identity and style has demonstrated promising results and provides an intuitive method of control. However, reliance on human-labeled descriptions prevents scaling to large datasets. Our work bridges the gap between these two approaches. We propose a scalable method for labeling various aspects of speaker identity, style, and recording conditions. We then apply this method to a 45k hour dataset, which we use to train a speech language model. Furthermore, we propose simple methods for increasing audio fidelity, significantly outperforming recent work despite relying entirely on found data. Our results demonstrate high-fidelity speech generation in a diverse range of accents, prosodic styles, channel conditions, and acoustic conditions, all accomplished with a single model and intuitive natural language conditioning. Audio samples can be heard at https://text-description-to-speech.com/.

We present MunTTS, an end-to-end text-to-speech (TTS) system specifically for Mundari, a low-resource Indian language of the Austo-Asiatic family. Our work addresses the gap in linguistic technology for underrepresented languages by collecting and processing data to build a speech synthesis system. We begin our study by gathering a substantial dataset of Mundari text and speech and train end-to-end speech models. We also delve into the methods used for training our models, ensuring they are efficient and effective despite the data constraints. We evaluate our system with native speakers and objective metrics, demonstrating its potential as a tool for preserving and promoting the Mundari language in the digital age.

Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an acoustic model that utilizes a rectified flow matching algorithm to achieve high synthesis quality with a limited number of sampling steps. VoiceFlow formulates the process of generating mel-spectrograms into an ordinary differential equation conditional on text inputs, whose vector field is then estimated. The rectified flow technique then effectively straightens its sampling trajectory for efficient synthesis. Subjective and objective evaluations on both single and multi-speaker corpora showed the superior synthesis quality of VoiceFlow compared to the diffusion counterpart. Ablation studies further verified the validity of the rectified flow technique in VoiceFlow.

This paper addresses a major challenge to historical research on the 19th century. Large quantities of sources have become digitally available for the first time, while extraction techniques are lagging behind. Therefore, we researched machine learning (ML) models to recognise and extract complex data structures in a high-value historical primary source, the Schematismus. It records every single person in the Habsburg civil service above a certain hierarchical level between 1702 and 1918 and documents the genesis of the central administration over two centuries. Its complex and intricate structure as well as its enormous size have so far made any more comprehensive analysis of the administrative and social structure of the later Habsburg Empire on the basis of this source impossible. We pursued two central objectives: Primarily, the improvement of the OCR quality, for which we considered an improved structure recognition to be essential; in the further course, it turned out that this also made the extraction of the data structure possible. We chose Faster R-CNN as base for the ML architecture for structure recognition. In order to obtain the required amount of training data quickly and economically, we synthesised Hof- und Staatsschematismus-style data, which we used to train our model. The model was then fine-tuned with a smaller set of manually annotated historical source data. We then used Tesseract-OCR, which was further optimised for the style of our documents, to complete the combined structure extraction and OCR process. Results show a significant decrease in the two standard parameters of OCR-performance, WER and CER (where lower values are better). Combined structure detection and fine-tuned OCR improved CER and WER values by remarkable 71.98 percent (CER) respectively 52.49 percent (WER).

Ubisoft's Prince of Persia: The Lost Crown launches next week, but players are likely to encounter an amusing bug as they make their way through the game, as reported by IGN. One of the game's NPCs is voiced by a text-to-speech program, complete with the slightly robotic tones we've come to associate with these services. It's not quite Siri or Alexa, but it's close and certainly doesn't fit the game's Persian-inspired setting. The NPC-in-question is a tree spirit named Kalux and seems to be voiced by a TTS program that's available online for free and typically used by streamers. This isn't an "AI is coming for your jobs" type thing, but rather a mistake on Ubisoft's part, as each and every other NPC is attached to a voice actor.

Mindfulness-based therapies have been shown to be effective in improving mental health, and technology-based methods have the potential to expand the accessibility of these therapies. To enable real-time personalized content generation for mindfulness practice in these methods, high-quality computer-synthesized text-to-speech (TTS) voices are needed to provide verbal guidance and respond to user performance and preferences. However, the user-perceived quality of state-of-the-art TTS voices has not yet been evaluated for administering mindfulness meditation, which requires emotional expressiveness. In addition, work has not yet been done to study the effect of physical embodiment and personalization on the user-perceived quality of TTS voices for mindfulness. To that end, we designed a two-phase human subject study. In Phase 1, an online Mechanical Turk between-subject study (N=471) evaluated 3 (feminine, masculine, child-like) state-of-the-art TTS voices with 2 (feminine, masculine) human therapists' voices in 3 different physical embodiment settings (no agent, conversational agent, socially assistive robot) with remote participants. Building on findings from Phase 1, in Phase 2, an in-person within-subject study (N=94), we used a novel framework we developed for personalizing TTS voices based on user preferences, and evaluated user-perceived quality compared to best-rated non-personalized voices from Phase 1. We found that the best-rated human voice was perceived better than all TTS voices; the emotional expressiveness and naturalness of TTS voices were poorly rated, while users were satisfied with the clarity of TTS voices. Surprisingly, by allowing users to fine-tune TTS voice features, the user-personalized TTS voices could perform almost as well as human voices, suggesting user personalization could be a simple and very effective tool to improve user-perceived quality of TTS voice.

Sinhala is the native language of the Sinhalese people who make up the largest ethnic group of Sri Lanka. The language belongs to the globe-spanning language tree, Indo-European. However, due to poverty in both linguistic and economic capital, Sinhala, in the perspective of Natural Language Processing tools and research, remains a resource-poor language which has neither the economic drive its cousin English has nor the sheer push of the law of numbers a language such as Chinese has. A number of research groups from Sri Lanka have noticed this dearth and the resultant dire need for proper tools and research for Sinhala natural language processing. However, due to various reasons, these attempts seem to lack coordination and awareness of each other. The objective of this paper is to fill that gap of a comprehensive literature survey of the publicly available Sinhala natural language tools and research so that the researchers working in this field can better utilize contributions of their peers. As such, we shall be uploading this paper to arXiv and perpetually update it periodically to reflect the advances made in the field.

ABSTRACT Parallel text-to-speech models have been widely applied for real-time speech synthesis, and they offer more controllability and a much faster synthesis process compared with conventional auto-regressive models. Although parallel models have benefits in many aspects, they become naturally unfit for incremental synthesis due to their fully parallel architecture such as transformer. In this work, we propose Incremental FastPitch, a novel FastPitch variant capable of incrementally producing high-quality Mel chunks by improving the architecture with chunk-based FFT blocks, training with receptivefield constrained chunk attention masks, and inference with fixed size past model states. Experimental results show that our proposal can produce speech quality comparable to the parallel FastPitch, with a significant lower latency that allows even lower response time for real-time speech applications. Index Terms-- text-to-speech, speech synthesis, realtime, low-latency, streaming tts 1. INTRODUCTION In recent years, Text-to-Speech (TTS) technology has witnessed Figure 1: Incremental FastPitch, Chunk-based FFT Block, and remarkable advancements, enabling the generation of Chunk Mask for Receptive-Filed Constrained Training natural and expressive speech from text inputs.

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages, utilizing discrete semantic tokens obtained from wav2vec2.0 embeddings. For a robust and efficient alignment modeling, we employ a neural transducer named token transducer for the semantic token prediction, benefiting from its hard monotonic alignment constraints. Subsequently, a non-autoregressive (NAR) speech generator efficiently synthesizes waveforms from these semantic tokens. Additionally, a reference speech controls temporal dynamics and acoustic conditions at each stage. This decoupled framework reduces the training complexity of TTS while allowing each stage to focus on semantic and acoustic modeling. Our experimental results on zero-shot adaptive TTS demonstrate that our model surpasses the baseline in terms of speech quality and speaker similarity, both objectively and subjectively. We also delve into the inference speed and prosody control capabilities of our approach, highlighting the potential of neural transducers in TTS frameworks.