白拾的笔记本

Helpful Materials: GitHub repo https://github.com/ramdrop/cue https://github.com/NVIDIA/MinkowskiEngine

65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa951388d187066e6a12bd1c6d157f10db3adecc89270ab26a17b62b33adfe35a600ef14bcc92c15ac3a36355bc651ac1116d8b76dabf93abe7ed14183ac75daaf6fc1be0700cfd2178ea55d6309c8341eea0e9050f79c2b46c671b2dba154a73482ff830171670aba95110b17b417dddd39116bd91aa8c54c9c83b751e9c5b0641d58adfae255c3f17f3c0dc8edc16ce545041c165e318ca75ecfe7882b1a103a5663def4b1af7c27b5a52334405fc0427dc6b66e0d6cc1f20734e2174e0f2f243562f8740f2d45908ae4912f78220c1dcad40f07d63adaa9fea ...

65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa95dee07c63ee55b1eb7d727a3289677f4e6c7d915b8bb775ffe6f17610d75e729003d062c9929b5d7e2b2357d49e5017821c4a11b0da24150bb4470a4e6c4e31cd18e1532e3b26c4f331afe0aa816028e7ea886ad2178c547f9b634979c3cf99d538999ef6b6cc13e13e4467724aeaad00e44438048694d4244e758842624aa2219b354d29b2cc31e8014dbdccd278702c30fa6d796f2b864434c7909157cb71726c0454bae0fa840538502e50ab908152751e141c8cc2acbc1daa9ac8191a632917fa275c11b6c5466aef8a8dad0a8255e761cecbb6669d0c2 ...

65f8e3b87362ab224b1b50bf77ce06905769e529ac2ce2fb173717936f4bfa953ddf2337fef7e8935e7f6faf9d9e071ac3cb5cfd8a6a29534f7778efa6a511c8fccceb9b420be6b9286cc5b475cc232ac9c1dc968eb881fafd7baadefd30bfbce8e88068fec97fb003fbe6446cac9668ee7124e7239ed2224d1469d4be982454e51590022664b433e5eb55598b4ae2905b17eb80290120c011b2d642b9c86c70fdb896829f9df65e359e06ada9482ce8f37d3fc003a4b7227a8ed7234578d849a779fedcd81a538b6e4e2a19fe572f27ee068585dc84bb254a093c8e9d564a0d411f1a85228c937fa8b5f85a53497acd16f12fcebb24a165c ...

From subword units to n-grams: hierarchy of modelsDefining a hierarchy of models: we can compile different HMMs to create models of utterances We can do some pruning, remove some tokens while proceeding, reduce computation cost (Maybe Heuristic is also can be helpful in such case.) Conditional independence and the forward algorithmWe use the Markov property of HMMs (i.e. conditional independence assumptions) to make computing probabilities of observation sequences easier HMM tra ...

Hidden Markov Models for ASRIntro to Hidden Markov Models, comparison to DTW. dynamic time warping (DTW) Hidden state sequences and alignmentHidden state sequence, Trellis (i.e. lattice) representation of an HMM, aligning observations to states grid and lattice The Viterbi algorithm and token passingThe Viterbi algorithm can be computed on different data structures. The token passing version turns out to be very convenient for ASR.Tthese two different implementations are simply two different w ...

Gaussian distributions in modelsClassification model If features are highly correlate with each other, we can solve this correlation by rotating the axis, by PCA. Gaussian distribution of classification result of feature vector Decision boundary Cepstral Analysis, Mel-FilterbanksWe now start thinking about what a good representation of the acoustic signal should be, motivating the use Mel-Frequency Cepstral Coefficients (MFCCs). Since the feature in a feature vector is correlated, if we want to ...

Mission, scenarios and behaviorsTask: Navigate the robot itself from the current position to final destination on the map, without human intervention. Goal: find most efficient path (trajectory) in terms of time or distance travelled. Example Common Behavior Sets Speed tracking Deceleration to stop Stay stopped Yield Emergency stop Motion planning constraints Read more about vehicle dynamic. Objective functions in planning Supplementary Readings Motion Planning For Au ...

Cochlea, Mel-Scale, FilterbanksFrom human speech perception to considerations for features for automatic speech recognition CochleaDifferent places along the cochlea respond to the incoming frequency. Mel scaleNonlinearity in hertz scale, linear in mal scale, for cochlea. Filter banksSimplify of cochlea is like a bank of bandpass filters.lower frequency limit and higher frequency limit. Wider and wider in higher frequency. triangular filters is more appropriate than the rectangle one sho ...

Connected and Citation SpeechConnected speech differs from the citation form. Connected Speech ProcessesConnected speech forms are highly variable as the result of a number of processes that apply to consonants and vowels. Prosodic StructureProsody is the combination of speech properties that break speech into units of time, indicate the boundaries of those units, and highlight certain constituents. A constituent is a word or a group of words that function as a single unit ...

Module 5 TTS front-end We want to generate speech that is Intelligible: you can clearly perceive what words are being said Natural: sounds like human speech Appropriate: conveys the right meaning in a specific context Front-end: Analyze text, generate a linguistic specification of what to actually generate Front-end purpose: derive a linguistic specification from text that includes the necessary information to generate speech Back-end: Waveform generation from the linguistic specification ...

Occupancy grid Occupancy Map Calculus Practicle issues of Occupancy map Inverse Measurement Model Downsampling for lidar Other Type of Map Supplementary Readings Note of Occupancy Maps. (MUST READ) Lanelets: Efficient Map Representation for Autonomous Driving. (Optional) Probabilistic robotics. Read Chapter 9 - Occupancy Grid Mapping for an overview of how occupancy grids are generated Origin: Dr. Chris Lu (Homepage)Translate + Edit: YangSier (Homepage) :four_leaf_clover:碎碎念:f ...

LiDAR LiDAR calculus State Estimation via Point Set RegressionProblem define ICP Algorithm Origin: Dr. Chris Lu (Homepage)Translate + Edit: YangSier (Homepage) :four_leaf_clover:碎碎念:four_leaf_clover:Hello米娜桑，这里是英国留学中的杨丝儿。我的博客的关键词集中在编程、算法、机器人、人工智能、数学等等，点个关注吧，持续高质量输出中。:cherry_blossom:唠嗑QQ群：兔叽的魔术工房 (942848525):star:B站账号：白拾Official（活跃于知识区和动画区）

The coordinate systems in mobile robotics world coordinate system ego-vehicle coordinate system Rigid Body AssumptionRigid Body is a solid body in which deformation is zero or so small it can be neglected. rigid body assumption implied that movement of a sensor mounted on the robot should be the same as other co-located sensors and the whole platform. Motion in generalMotion that can be described by a rotation and translation. There are 6 degree of freedom (DoF) in 3D space for rigid body. ...