We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration model. A simple but effective method to achieve emphasized speech consists in increasing the predicted duration of the emphasised word. We show that this is significantly better than spectrogram modification techniques improving naturalness by $7.3\%$ and correct testers' identification of the emphasized word in a sentence by $40\%$ on a reference female en-US voice. We show that this technique significantly closes the gap to methods that require explicit recordings. The method proved to be scalable and preferred in all four languages tested (English, Spanish, Italian, German), for different voices and multiple speaking styles.
相關內容
語音合成（Speech Synthesis），也稱為文語轉換（Text-to-Speech, TTS,它是將任意的輸入文本轉換成自然流暢的語音輸出。語音合成涉及到人工智能、心理學、聲學、語言學、數字信號處理、計算機科學等多個學科技術，是信息處理領域中的一項前沿技術。
隨著計算機技術的不斷提高，語音合成技術從早期的共振峰合成,逐步發展為波形拼接合成和統計參數語音合成，再發展到混合語音合成；合成語音的質量、自然度已經得到明顯提高，基本能滿足一些特定場合的應用需求。目前，語音合成技術在銀行、醫院等的信息播報系統、汽車導航系統、自動應答呼叫中心等都有廣泛應用，取得了巨大的經濟效益。
另外，隨著智能手機、MP3、PDA 等與我們生活密切相關的媒介的大量涌現，語音合成的應用也在逐漸向娛樂、語音教學、康復治療等領域深入。可以說語音合成正在影響著人們生活的方方面面。
Decoder-only Large Language Models (LLMs) have demonstrated potential in machine translation (MT), albeit with performance slightly lagging behind traditional encoder-decoder Neural Machine Translation (NMT) systems. However, LLMs offer a unique advantage: the ability to control the properties of the output through prompts. In this study, we harness this flexibility to explore LLaMa's capability to produce gender-specific translations for languages with grammatical gender. Our results indicate that LLaMa can generate gender-specific translations with competitive accuracy and gender bias mitigation when compared to NLLB, a state-of-the-art multilingual NMT system. Furthermore, our experiments reveal that LLaMa's translations are robust, showing significant performance drops when evaluated against opposite-gender references in gender-ambiguous datasets but maintaining consistency in less ambiguous contexts. This research provides insights into the potential and challenges of using LLMs for gender-specific translations and highlights the importance of in-context learning to elicit new tasks in LLMs.
We extend nonparametric regression smoothing splines to a context where there is endogeneity and instrumental variables are available. Unlike popular existing estimators, the resulting estimator is one-step and relies on a unique regularization parameter. We derive uniform rates of the convergence for the estimator and its first derivative. We also address the issue of imposing monotonicity in estimation. Simulations confirm the good performances of our estimator compared to some popular two-step procedures. Our method yields economically sensible results when used to estimate Engel curves.
Autonomous Vehicles (AVs) being developed these days rely on various sensor technologies to sense and perceive the world around them. The sensor outputs are subsequently used by the Automated Driving System (ADS) onboard the vehicle to make decisions that affect its trajectory and how it interacts with the physical world. The main sensor technologies being utilized for sensing and perception (S&P) are LiDAR (Light Detection and Ranging), camera, RADAR (Radio Detection and Ranging), and ultrasound. Different environmental parameters would have different effects on the performance of each sensor, thereby affecting the S&P and decision-making (DM) of an AV. In this publication, we explore the effects of different environmental parameters on LiDARs and cameras, leading us to conduct a study to better understand the impact of several of these parameters on LiDAR performance. From the experiments undertaken, the goal is to identify some of the weaknesses and challenges that a LiDAR may face when an AV is using it. This informs AV regulators in Singapore of the effects of different environmental parameters on AV sensors so that they can determine testing standards and specifications which will assess the adequacy of LiDAR systems installed for local AV operations more robustly. Our approach adopts the LiDAR test methodology first developed in the Urban Mobility Grand Challenge (UMGC-L010) White Paper on LiDAR performance against selected Automotive Paints.
In this work, we develop first-order (Hessian-free) and zero-order (derivative-free) implementations of the Cubically regularized Newton method for solving general non-convex optimization problems. For that, we employ finite difference approximations of the derivatives. We use a special adaptive search procedure in our algorithms, which simultaneously fits both the regularization constant and the parameters of the finite difference approximations. It makes our schemes free from the need to know the actual Lipschitz constants. Additionally, we equip our algorithms with the lazy Hessian update that reuse a previously computed Hessian approximation matrix for several iterations. Specifically, we prove the global complexity bound of $\mathcal{O}( n^{1/2} \epsilon^{-3/2})$ function and gradient evaluations for our new Hessian-free method, and a bound of $\mathcal{O}( n^{3/2} \epsilon^{-3/2} )$ function evaluations for the derivative-free method, where $n$ is the dimension of the problem and $\epsilon$ is the desired accuracy for the gradient norm. These complexity bounds significantly improve the previously known ones in terms of the joint dependence on $n$ and $\epsilon$, for the first-order and zeroth-order non-convex optimization.
Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be denoised by speech enhancement models. Noise-robust TTS models are often trained using the enhanced speech, which thus suffer from speech distortion and background noise that affect the quality of the synthesized speech. Meanwhile, it was shown that self-supervised pre-trained models exhibit excellent noise robustness on many speech tasks, implying that the learned representation has a better tolerance for noise perturbations. In this work, we therefore explore pre-trained models to improve the noise robustness of TTS models. Based on HiFi-GAN, we first propose a representation-to-waveform vocoder, which aims to learn to map the representation of pre-trained models to the waveform. We then propose a text-to-representation FastSpeech2 model, which aims to learn to map text to pre-trained model representations. Experimental results on the LJSpeech and LibriTTS datasets show that our method outperforms those using speech enhancement methods in both subjective and objective metrics. Audio samples are available at: //zqs01.github.io/rep2wav.
We provide a new sequent calculus that enjoys syntactic cut-elimination and strongly terminating backward proof search for the intuitionistic Strong L\"ob logic $\sf{iSL}$, an intuitionistic modal logic with a provability interpretation. A novel measure on sequents is used to prove both the termination of the naive backward proof search strategy, and the admissibility of cut in a syntactic and direct way, leading to a straightforward cut-elimination procedure. All proofs have been formalised in the interactive theorem prover Coq.
This paper presents another improved version of Plantard arithmetic that could speed up Kyber implementations on two low-end 32-bit IoT platforms (ARM Cortex-M3 and RISC-V) without SIMD extensions. Specifically, we further enlarge the input range of the Plantard arithmetic without modifying its computation steps. After tailoring the Plantard arithmetic for Kyber's modulus, we show that the input range of the Plantard multiplication by a constant is at least 2.45 times larger than the original design in TCHES2022. Then, two optimization techniques for efficient Plantard arithmetic on Cortex-M3 and RISC-V are presented. We show that the Plantard arithmetic supersedes both Montgomery and Barrett arithmetic on low-end 32-bit platforms. With the enlarged input range and the efficient implementation of the Plantard arithmetic on these platforms, we propose various optimization strategies for NTT/INTT. We minimize or entirely eliminate the modular reduction of coefficients in NTT/INTT by taking advantage of the larger input range of the proposed Plantard arithmetic on low-end 32-bit platforms. Furthermore, we propose two memory optimization strategies that reduce 23.50% to 28.31% stack usage for the speed-version Kyber implementation when compared to its counterpart on Cortex-M4. The proposed optimizations make the speed-version implementation more feasible on low-end IoT devices. Thanks to the aforementioned optimizations, our NTT/INTT implementation shows considerable speedups compared to the state-of-the-art work. Overall, we demonstrate the applicability of the speed-version Kyber implementation on memory-constrained IoT platforms and set new speed records for Kyber on these platforms.
Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been explored. Furthermore there is a lack of systematic evaluation across diverse domains. In this work, we propose pre-training large Transformer-based encoder-decoder models on massive text corpora with a new self-supervised objective. In PEGASUS, important sentences are removed/masked from an input document and are generated together as one output sequence from the remaining sentences, similar to an extractive summary. We evaluated our best PEGASUS model on 12 downstream summarization tasks spanning news, science, stories, instructions, emails, patents, and legislative bills. Experiments demonstrate it achieves state-of-the-art performance on all 12 downstream datasets measured by ROUGE scores. Our model also shows surprising performance on low-resource summarization, surpassing previous state-of-the-art results on 6 datasets with only 1000 examples. Finally we validated our results using human evaluation and show that our model summaries achieve human performance on multiple datasets.
We propose a novel single shot object detection network named Detection with Enriched Semantics (DES). Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module. The segmentation branch is supervised by weak segmentation ground-truth, i.e., no extra annotation is required. In conjunction with that, we employ a global activation module which learns relationship between channels and object classes in a self-supervised manner. Comprehensive experimental results on both PASCAL VOC and MS COCO detection datasets demonstrate the effectiveness of the proposed method. In particular, with a VGG16 based DES, we achieve an mAP of 81.7 on VOC2007 test and an mAP of 32.8 on COCO test-dev with an inference speed of 31.5 milliseconds per image on a Titan Xp GPU. With a lower resolution version, we achieve an mAP of 79.7 on VOC2007 with an inference speed of 13.0 milliseconds per image.
This paper reports Deep LOGISMOS approach to 3D tumor segmentation by incorporating boundary information derived from deep contextual learning to LOGISMOS - layered optimal graph image segmentation of multiple objects and surfaces. Accurate and reliable tumor segmentation is essential to tumor growth analysis and treatment selection. A fully convolutional network (FCN), UNet, is first trained using three adjacent 2D patches centered at the tumor, providing contextual UNet segmentation and probability map for each 2D patch. The UNet segmentation is then refined by Gaussian Mixture Model (GMM) and morphological operations. The refined UNet segmentation is used to provide the initial shape boundary to build a segmentation graph. The cost for each node of the graph is determined by the UNet probability maps. Finally, a max-flow algorithm is employed to find the globally optimal solution thus obtaining the final segmentation. For evaluation, we applied the method to pancreatic tumor segmentation on a dataset of 51 CT scans, among which 30 scans were used for training and 21 for testing. With Deep LOGISMOS, DICE Similarity Coefficient (DSC) and Relative Volume Difference (RVD) reached 83.2+-7.8% and 18.6+-17.4% respectively, both are significantly improved (p<0.05) compared with contextual UNet and/or LOGISMOS alone.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191