Nevertheless, the nuance of references might be difficult to be captured by these models State-of-the-art Text-To-Speech (TTS) models are capable (e.g. one sad and one depressed reference might produce of producing high-quality speech. The generated speech, the same synthesized speech), due to a mismatch between the however, is usually neutral in emotional expression, whereas content or speaker of the reference and synthesized speech, very often one would want fine-grained emotional control which implies the inflexible controllability of these models. of words or phonemes. Although still challenging, the first A better approach to achieve fine-grained controllable TTS models have been recently proposed that are able to emotional TTS is by manually assigning intensity labels (such control voice by manually assigning emotion intensity. Unfortunately, as strong or weak happiness) on words or phonemes, which due to the neglect of intra-class distance, the provides a flexible and efficient way to control the emotion intensity differences are often unrecognizable.

For years, creating good voice overs meant investing hundreds if not thousands of dollars in hiring voice artists, renting a recording studio to get the script recorded, investing in expensive recording equipment (if you are recording from home), and recruiting or outsourcing the entire project to an audio editor to mix the audio and produce a high-quality voiceover. Not to mention, the valuable hours dedicated to the entire process. Even after all this, the quality of the produced audio file may be subpar. What if there was an alternative to creating studio-quality voiceovers, and that too from the comfort of your own homes? Introducing Murf AI voice generator, which eliminates the entire process of generating voiceovers manually and enables you to quickly produce human-like voiceovers without any specialized hardware or professional. Leveraging advanced AI algorithms and deep learning, the realistic online voice generator tool allows you to convert text into natural-sounding speech, in a matter of just a few minutes.

Many popular machine learning models scale poorly when deployed on CPUs. In this paper we explore the reasons why and propose a simple, yet effective approach based on the well-known Divide-and-Conquer Principle to tackle this problem of great practical importance. Given an inference job, instead of using all available computing resources (i.e., CPU cores) for running it, the idea is to break the job into independent parts that can be executed in parallel, each with the number of cores according to its expected computational cost. We implement this idea in the popular OnnxRuntime framework and evaluate its effectiveness with several use cases, including the well-known models for optical character recognition (PaddleOCR) and natural language processing (BERT).

At present, Text-to-speech (TTS) systems that are trained with high-quality transcribed speech data using end-to-end neural models can generate speech that is intelligible, natural, and closely resembles human speech. These models are trained with relatively large single-speaker professionally recorded audio, typically extracted from audiobooks. Meanwhile, due to the scarcity of freely available speech corpora of this kind, a larger gap exists in Arabic TTS research and development. Most of the existing freely available Arabic speech corpora are not suitable for TTS training as they contain multi-speaker casual speech with variations in recording conditions and quality, whereas the corpus curated for speech synthesis are generally small in size and not suitable for training state-of-the-art end-to-end models. In a move towards filling this gap in resources, we present a speech corpus for Classical Arabic Text-to-Speech (ClArTTS) to support the development of end-to-end TTS systems for Arabic. The speech is extracted from a LibriVox audiobook, which is then processed, segmented, and manually transcribed and annotated. The final ClArTTS corpus contains about 12 hours of speech from a single male speaker sampled at 40100 kHz. In this paper, we describe the process of corpus creation and provide details of corpus statistics and a comparison with existing resources. Furthermore, we develop two TTS systems based on Grad-TTS and Glow-TTS and illustrate the performance of the resulting systems via subjective and objective evaluations. The corpus will be made publicly available at www.clartts.com for research purposes, along with the baseline TTS systems demo.

The goal of this work is zero-shot text-to-speech synthesis, with speaking styles and voices learnt from facial characteristics. Inspired by the natural fact that people can imagine the voice of someone when they look at his or her face, we introduce a face-styled diffusion text-to-speech (TTS) model within a unified framework learnt from visible attributes, called Face-TTS. This is the first time that face images are used as a condition to train a TTS model. We jointly train cross-model biometrics and TTS models to preserve speaker identity between face images and generated speech segments. We also propose a speaker feature binding loss to enforce the similarity of the generated and the ground truth speech segments in speaker embedding space. Since the biometric information is extracted directly from the face image, our method does not require extra fine-tuning steps to generate speech from unseen and unheard speakers. We train and evaluate the model on the LRS3 dataset, an in-the-wild audio-visual corpus containing background noise and diverse speaking styles. The project page is https://facetts.github.io.

There has been recent interest in improving optical character recognition (OCR) for endangered languages, particularly because a large number of documents and books in these languages are not in machine-readable formats. The performance of OCR systems is typically evaluated using automatic metrics such as character and word error rates. While error rates are useful for the comparison of different models and systems, they do not measure whether and how the transcriptions produced from OCR tools are useful to downstream users. In this paper, we present a human-centric evaluation of OCR systems, focusing on the Kwak'wala language as a case study. With a user study, we show that utilizing OCR reduces the time spent in the manual transcription of culturally valuable documents -- a task that is often undertaken by endangered language community members and researchers -- by over 50%. Our results demonstrate the potential benefits that OCR tools can have on downstream language documentation and revitalization efforts.

Last year, Samsung introduced a feature called "Text Call" for Bixby with One UI 5, which essentially transforms voice calls into written text and vice versa. It was initially available in Korean, but now the company has launched support for the feature in (US) English. The feature lets users answer calls by typing a message that Bixby will then read out loud to the caller. It can also transcribe what the caller says, making it a pretty useful tool for those hard of hearing or for anyone taking a call in a noisy environment. While Bixby has several voice options, Samsung is giving users the capability to personalize the voice it uses to answer calls.

We propose a lightweight end-to-end text-to-speech model using multi-band generation and inverse short-time Fourier transform. Our model is based on VITS, a high-quality end-to-end text-to-speech model, but adopts two changes for more efficient inference: 1) the most computationally expensive component is partially replaced with a simple inverse short-time Fourier transform, and 2) multi-band generation, with fixed or trainable synthesis filters, is used to generate waveforms. Unlike conventional lightweight models, which employ optimization or knowledge distillation separately to train two cascaded components, our method enjoys the full benefits of end-to-end optimization. Experimental results show that our model synthesized speech as natural as that synthesized by VITS, while achieving a real-time factor of 0.066 on an Intel Core i7 CPU, 4.1 times faster than VITS. Moreover, a smaller version of the model significantly outperformed a lightweight baseline model with respect to both naturalness and inference speed. Code and audio samples are available from https://github.com/MasayaKawamura/MB-iSTFT-VITS.

Although current neural text-to-speech (TTS) models are able to generate high-quality speech, intensity controllable emotional TTS is still a challenging task. Most existing methods need external optimizations for intensity calculation, leading to suboptimal results or degraded quality. In this paper, we propose EmoDiff, a diffusion-based TTS model where emotion intensity can be manipulated by a proposed soft-label guidance technique derived from classifier guidance. Specifically, instead of being guided with a one-hot vector for the specified emotion, EmoDiff is guided with a soft label where the value of the specified emotion and \textit{Neutral} is set to $\alpha$ and $1-\alpha$ respectively. The $\alpha$ here represents the emotion intensity and can be chosen from 0 to 1. Our experiments show that EmoDiff can precisely control the emotion intensity while maintaining high voice quality. Moreover, diverse speech with specified emotion intensity can be generated by sampling in the reverse denoising process.

An ongoing challenge in current natural language processing is how its major advancements tend to disproportionately favor resource-rich languages, leaving a significant number of under-resourced languages behind. Due to the lack of resources required to train and evaluate models, most modern language technologies are either nonexistent or unreliable to process endangered, local, and non-standardized languages. Optical character recognition (OCR) is often used to convert endangered language documents into machine-readable data. However, such OCR output is typically noisy, and most word alignment models are not built to work under such noisy conditions. In this work, we study the existing word-level alignment models under noisy settings and aim to make them more robust to noisy data. Our noise simulation and structural biasing method, tested on multiple language pairs, manages to reduce the alignment error rate on a state-of-the-art neural-based alignment model up to 59.6%.